{ "schema": 1, "runId": "learning-bug-v01-20261027", "executedAt": "2026-10-27T10:59:05.674Z", "model": "Synthetic two-choice delta-rule associative learner; no biological connectome", "version": "1.0.0", "environment": { "platform": "linux", "architecture": "x64", "node": "v22.23.4" }, "source": { "path": "/experiments/learning-bug/model.mjs", "sha256": "cb226b497a49ed78979e0327ebe66bebeae2d1edbeafb6ad2d3fba19e19ce183", "benchmarkPath": "/experiments/learning-bug/benchmark.mjs", "benchmarkSha256": "328920eee1620a2084a394bbfda126a19a4fee83823791d8e1108d9231a5d23f" }, "parameters": { "alpha": 0.2, "inverseTemperature": 6, "exploration": 0.1 }, "protocol": [ { "id": "baseline", "name": "Before learning", "trials": 20, "rewarded": "A", "plastic": false, "connected": true }, { "id": "acquisition", "name": "Learn A", "trials": 80, "rewarded": "A", "plastic": true, "connected": true }, { "id": "reversal", "name": "Switch to B", "trials": 80, "rewarded": "B", "plastic": true, "connected": true }, { "id": "disconnect", "name": "Disconnect memory", "trials": 40, "rewarded": "B", "plastic": false, "connected": false }, { "id": "restore", "name": "Reconnect memory", "trials": 40, "rewarded": "B", "plastic": false, "connected": true } ], "evaluation": { "trialsPerCheckpoint": 1000, "plasticity": false, "freshStream": true, "matchedDraws": true, "note": "Reversal, disconnection and restoration share assessment draws; exact restoration is a deterministic implementation control, not biological evidence." }, "acceptance": { "predeclared": true, "acquisition": "assessment reward advantage >= 0.25", "reversal": "assessment reward advantage >= 0.25", "disconnect": "reward rate drop >= 0.25 from reversal", "restore": "exact reversal assessment reward rate", "preservedMemory": "no stored value change during disconnect or restore", "frozenControl": "control values stay zero" }, "aggregate": { "baseline": { "control": { "mean": 0.5041, "min": 0.468, "max": 0.539 }, "learner": { "mean": 0.5041, "min": 0.468, "max": 0.539 } }, "acquisition": { "control": { "mean": 0.5041, "min": 0.468, "max": 0.539 }, "learner": { "mean": 0.9490666666666667, "min": 0.937, "max": 0.961 } }, "reversal": { "control": { "mean": 0.49589999999999995, "min": 0.461, "max": 0.532 }, "learner": { "mean": 0.9424333333333335, "min": 0.925, "max": 0.956 } }, "disconnect": { "control": { "mean": 0.49589999999999995, "min": 0.461, "max": 0.532 }, "learner": { "mean": 0.49589999999999995, "min": 0.461, "max": 0.532 } }, "restore": { "control": { "mean": 0.49589999999999995, "min": 0.461, "max": 0.532 }, "learner": { "mean": 0.9424333333333335, "min": 0.925, "max": 0.956 } } }, "seeds": 30, "trainingTrials": 7800, "assessmentTrials": 300000, "failedSeeds": [], "runs": [ { "seed": 1, "evaluationSeed": 2654435768, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 491, "rate": 0.491, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 491, "rate": 0.491, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.6, "learner": 0.6 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999568640854, "B": 0 } }, "control": { "trials": 1000, "rewards": 491, "rate": 0.491, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 952, "rate": 0.952, "pA": 0.9477746385844948, "expectedReward": 0.9477746385844948 }, "observedTrainingReward": { "control": 0.4875, "learner": 0.95 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.02814749645689755, "B": 0.9999993722898265 } }, "control": { "trials": 1000, "rewards": 509, "rate": 0.509, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 948, "rate": 0.948, "pA": 0.05263360332135058, "expectedReward": 0.9473663966786494 }, "observedTrainingReward": { "control": 0.5, "learner": 0.8 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.02814749645689755, "B": 0.9999993722898265 } }, "control": { "trials": 1000, "rewards": 509, "rate": 0.509, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 509, "rate": 0.509, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.375, "learner": 0.375 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.02814749645689755, "B": 0.9999993722898265 } }, "control": { "trials": 1000, "rewards": 509, "rate": 0.509, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 948, "rate": 0.948, "pA": 0.05263360332135058, "expectedReward": 0.9473663966786494 }, "observedTrainingReward": { "control": 0.425, "learner": 0.975 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 2, "evaluationSeed": 2654435771, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 514, "rate": 0.514, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 514, "rate": 0.514, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.6, "learner": 0.6 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999157501667, "B": 0 } }, "control": { "trials": 1000, "rewards": 514, "rate": 0.514, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 958, "rate": 0.958, "pA": 0.9477746380368922, "expectedReward": 0.9477746380368922 }, "observedTrainingReward": { "control": 0.425, "learner": 0.9125 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.018014396991771913, "B": 0.9999990192028538 } }, "control": { "trials": 1000, "rewards": 486, "rate": 0.486, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 936, "rate": 0.936, "pA": 0.052478687369287645, "expectedReward": 0.9475213126307124 }, "observedTrainingReward": { "control": 0.4, "learner": 0.775 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.018014396991771913, "B": 0.9999990192028538 } }, "control": { "trials": 1000, "rewards": 486, "rate": 0.486, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 486, "rate": 0.486, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.575, "learner": 0.575 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.018014396991771913, "B": 0.9999990192028538 } }, "control": { "trials": 1000, "rewards": 486, "rate": 0.486, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 936, "rate": 0.936, "pA": 0.052478687369287645, "expectedReward": 0.9475213126307124 }, "observedTrainingReward": { "control": 0.525, "learner": 0.9 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 3, "evaluationSeed": 2654435770, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 510, "rate": 0.51, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 510, "rate": 0.51, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999157501667, "B": 0 } }, "control": { "trials": 1000, "rewards": 510, "rate": 0.51, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 937, "rate": 0.937, "pA": 0.9477746380368922, "expectedReward": 0.9477746380368922 }, "observedTrainingReward": { "control": 0.45, "learner": 0.9125 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589933868299443, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 490, "rate": 0.49, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 936, "rate": 0.936, "pA": 0.053719727579658406, "expectedReward": 0.9462802724203416 }, "observedTrainingReward": { "control": 0.5125, "learner": 0.8625 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589933868299443, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 490, "rate": 0.49, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 490, "rate": 0.49, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.45, "learner": 0.45 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589933868299443, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 490, "rate": 0.49, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 936, "rate": 0.936, "pA": 0.053719727579658406, "expectedReward": 0.9462802724203416 }, "observedTrainingReward": { "control": 0.45, "learner": 0.975 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 4, "evaluationSeed": 2654435773, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 539, "rate": 0.539, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 539, "rate": 0.539, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.45, "learner": 0.45 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999998946877083, "B": 0 } }, "control": { "trials": 1000, "rewards": 539, "rate": 0.539, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 955, "rate": 0.955, "pA": 0.9477746377563581, "expectedReward": 0.9477746377563581 }, "observedTrainingReward": { "control": 0.425, "learner": 0.9 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.2097151779144117, "B": 0.9999999157501667 } }, "control": { "trials": 1000, "rewards": 461, "rate": 0.461, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 933, "rate": 0.933, "pA": 0.057783455868373405, "expectedReward": 0.9422165441316266 }, "observedTrainingReward": { "control": 0.55, "learner": 0.9125 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.2097151779144117, "B": 0.9999999157501667 } }, "control": { "trials": 1000, "rewards": 461, "rate": 0.461, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 461, "rate": 0.461, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.525, "learner": 0.525 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.2097151779144117, "B": 0.9999999157501667 } }, "control": { "trials": 1000, "rewards": 461, "rate": 0.461, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 933, "rate": 0.933, "pA": 0.057783455868373405, "expectedReward": 0.9422165441316266 }, "observedTrainingReward": { "control": 0.4, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 5, "evaluationSeed": 2654435772, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 532, "rate": 0.532, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 532, "rate": 0.532, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999568640854, "B": 0 } }, "control": { "trials": 1000, "rewards": 532, "rate": 0.532, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 951, "rate": 0.951, "pA": 0.9477746385844948, "expectedReward": 0.9477746385844948 }, "observedTrainingReward": { "control": 0.6125, "learner": 0.95 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947377172252, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 468, "rate": 0.468, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 944, "rate": 0.944, "pA": 0.053356760733876935, "expectedReward": 0.946643239266123 }, "observedTrainingReward": { "control": 0.5, "learner": 0.85 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947377172252, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 468, "rate": 0.468, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 468, "rate": 0.468, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.475, "learner": 0.475 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947377172252, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 468, "rate": 0.468, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 944, "rate": 0.944, "pA": 0.053356760733876935, "expectedReward": 0.946643239266123 }, "observedTrainingReward": { "control": 0.575, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 6, "evaluationSeed": 2654435775, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 520, "rate": 0.52, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 520, "rate": 0.52, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.45, "learner": 0.45 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999326001333, "B": 0 } }, "control": { "trials": 1000, "rewards": 520, "rate": 0.52, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 953, "rate": 0.953, "pA": 0.9477746382613196, "expectedReward": 0.9477746382613196 }, "observedTrainingReward": { "control": 0.5625, "learner": 0.925 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947210431642, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 480, "rate": 0.48, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 946, "rate": 0.946, "pA": 0.053356760700419684, "expectedReward": 0.9466432392995803 }, "observedTrainingReward": { "control": 0.4875, "learner": 0.85 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947210431642, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 480, "rate": 0.48, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 480, "rate": 0.48, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.525, "learner": 0.525 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947210431642, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 480, "rate": 0.48, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 946, "rate": 0.946, "pA": 0.053356760700419684, "expectedReward": 0.9466432392995803 }, "observedTrainingReward": { "control": 0.45, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 7, "evaluationSeed": 2654435774, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 496, "rate": 0.496, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 496, "rate": 0.496, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.45, "learner": 0.45 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999997943119303, "B": 0 } }, "control": { "trials": 1000, "rewards": 496, "rate": 0.496, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 954, "rate": 0.954, "pA": 0.9477746364194367, "expectedReward": 0.9477746364194367 }, "observedTrainingReward": { "control": 0.375, "learner": 0.8625 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.16777212549126824, "B": 0.9999998946877083 } }, "control": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 948, "rate": 0.948, "pA": 0.0560633851929789, "expectedReward": 0.9439366148070211 }, "observedTrainingReward": { "control": 0.5375, "learner": 0.9 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.16777212549126824, "B": 0.9999998946877083 } }, "control": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.575, "learner": 0.575 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.16777212549126824, "B": 0.9999998946877083 } }, "control": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 948, "rate": 0.948, "pA": 0.0560633851929789, "expectedReward": 0.9439366148070211 }, "observedTrainingReward": { "control": 0.55, "learner": 0.925 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 8, "evaluationSeed": 2654435761, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 502, "rate": 0.502, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 502, "rate": 0.502, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.5, "learner": 0.5 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999326001333, "B": 0 } }, "control": { "trials": 1000, "rewards": 502, "rate": 0.502, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 949, "rate": 0.949, "pA": 0.9477746382613196, "expectedReward": 0.9477746382613196 }, "observedTrainingReward": { "control": 0.475, "learner": 0.925 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.16777214869217877, "B": 0.9999998946877083 } }, "control": { "trials": 1000, "rewards": 498, "rate": 0.498, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 932, "rate": 0.932, "pA": 0.05606338603134881, "expectedReward": 0.9439366139686511 }, "observedTrainingReward": { "control": 0.525, "learner": 0.9 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.16777214869217877, "B": 0.9999998946877083 } }, "control": { "trials": 1000, "rewards": 498, "rate": 0.498, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 498, "rate": 0.498, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.5, "learner": 0.5 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.16777214869217877, "B": 0.9999998946877083 } }, "control": { "trials": 1000, "rewards": 498, "rate": 0.498, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 932, "rate": 0.932, "pA": 0.05606338603134881, "expectedReward": 0.9439366139686511 }, "observedTrainingReward": { "control": 0.5, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 9, "evaluationSeed": 2654435760, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 501, "rate": 0.501, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 501, "rate": 0.501, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.4, "learner": 0.4 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999460801067, "B": 0 } }, "control": { "trials": 1000, "rewards": 501, "rate": 0.501, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 954, "rate": 0.954, "pA": 0.9477746384408615, "expectedReward": 0.9477746384408615 }, "observedTrainingReward": { "control": 0.4125, "learner": 0.9375 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947303065315, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 499, "rate": 0.499, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 948, "rate": 0.948, "pA": 0.053356760719007044, "expectedReward": 0.9466432392809929 }, "observedTrainingReward": { "control": 0.5375, "learner": 0.85 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947303065315, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 499, "rate": 0.499, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 499, "rate": 0.499, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.45, "learner": 0.45 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947303065315, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 499, "rate": 0.499, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 948, "rate": 0.948, "pA": 0.053356760719007044, "expectedReward": 0.9466432392809929 }, "observedTrainingReward": { "control": 0.45, "learner": 0.975 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 10, "evaluationSeed": 2654435763, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 505, "rate": 0.505, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 505, "rate": 0.505, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999460801067, "B": 0 } }, "control": { "trials": 1000, "rewards": 505, "rate": 0.505, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 961, "rate": 0.961, "pA": 0.9477746384408615, "expectedReward": 0.9477746384408615 }, "observedTrainingReward": { "control": 0.4625, "learner": 0.9375 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589934128831643, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 495, "rate": 0.495, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 955, "rate": 0.955, "pA": 0.05371972763756461, "expectedReward": 0.9462802723624354 }, "observedTrainingReward": { "control": 0.4875, "learner": 0.8625 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589934128831643, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 495, "rate": 0.495, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 495, "rate": 0.495, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.475, "learner": 0.475 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589934128831643, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 495, "rate": 0.495, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 955, "rate": 0.955, "pA": 0.05371972763756461, "expectedReward": 0.9462802723624354 }, "observedTrainingReward": { "control": 0.425, "learner": 0.925 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 11, "evaluationSeed": 2654435762, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 512, "rate": 0.512, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 512, "rate": 0.512, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.4, "learner": 0.4 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999568640854, "B": 0 } }, "control": { "trials": 1000, "rewards": 512, "rate": 0.512, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 940, "rate": 0.94, "pA": 0.9477746385844948, "expectedReward": 0.9477746385844948 }, "observedTrainingReward": { "control": 0.475, "learner": 0.95 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 488, "rate": 0.488, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 926, "rate": 0.926, "pA": 0.05309197092549577, "expectedReward": 0.9469080290745042 }, "observedTrainingReward": { "control": 0.5125, "learner": 0.8375 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 488, "rate": 0.488, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 488, "rate": 0.488, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 488, "rate": 0.488, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 926, "rate": 0.926, "pA": 0.05309197092549577, "expectedReward": 0.9469080290745042 }, "observedTrainingReward": { "control": 0.45, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 12, "evaluationSeed": 2654435765, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 523, "rate": 0.523, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 523, "rate": 0.523, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.45, "learner": 0.45 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999568640854, "B": 0 } }, "control": { "trials": 1000, "rewards": 523, "rate": 0.523, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 950, "rate": 0.95, "pA": 0.9477746385844948, "expectedReward": 0.9477746385844948 }, "observedTrainingReward": { "control": 0.6125, "learner": 0.95 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 477, "rate": 0.477, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 931, "rate": 0.931, "pA": 0.05309197092549577, "expectedReward": 0.9469080290745042 }, "observedTrainingReward": { "control": 0.4625, "learner": 0.8375 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 477, "rate": 0.477, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 477, "rate": 0.477, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 477, "rate": 0.477, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 931, "rate": 0.931, "pA": 0.05309197092549577, "expectedReward": 0.9469080290745042 }, "observedTrainingReward": { "control": 0.55, "learner": 0.975 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 13, "evaluationSeed": 2654435764, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 505, "rate": 0.505, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 505, "rate": 0.505, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999654912683, "B": 0 } }, "control": { "trials": 1000, "rewards": 505, "rate": 0.505, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 945, "rate": 0.945, "pA": 0.9477746386994018, "expectedReward": 0.9477746386994018 }, "observedTrainingReward": { "control": 0.4875, "learner": 0.9625 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.03518437087466394, "B": 0.9999994978318612 } }, "control": { "trials": 1000, "rewards": 495, "rate": 0.495, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 956, "rate": 0.956, "pA": 0.052746829402446904, "expectedReward": 0.9472531705975531 }, "observedTrainingReward": { "control": 0.4375, "learner": 0.8125 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.03518437087466394, "B": 0.9999994978318612 } }, "control": { "trials": 1000, "rewards": 495, "rate": 0.495, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 495, "rate": 0.495, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.6, "learner": 0.6 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.03518437087466394, "B": 0.9999994978318612 } }, "control": { "trials": 1000, "rewards": 495, "rate": 0.495, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 956, "rate": 0.956, "pA": 0.052746829402446904, "expectedReward": 0.9472531705975531 }, "observedTrainingReward": { "control": 0.375, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 14, "evaluationSeed": 2654435767, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 472, "rate": 0.472, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 472, "rate": 0.472, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.5, "learner": 0.5 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999568640854, "B": 0 } }, "control": { "trials": 1000, "rewards": 472, "rate": 0.472, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 945, "rate": 0.945, "pA": 0.9477746385844948, "expectedReward": 0.9477746385844948 }, "observedTrainingReward": { "control": 0.4875, "learner": 0.95 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.043980463213902414, "B": 0.9999995982654889 } }, "control": { "trials": 1000, "rewards": 528, "rate": 0.528, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 939, "rate": 0.939, "pA": 0.052895210636092795, "expectedReward": 0.9471047893639072 }, "observedTrainingReward": { "control": 0.4875, "learner": 0.825 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.043980463213902414, "B": 0.9999995982654889 } }, "control": { "trials": 1000, "rewards": 528, "rate": 0.528, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 528, "rate": 0.528, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.043980463213902414, "B": 0.9999995982654889 } }, "control": { "trials": 1000, "rewards": 528, "rate": 0.528, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 939, "rate": 0.939, "pA": 0.052895210636092795, "expectedReward": 0.9471047893639072 }, "observedTrainingReward": { "control": 0.5, "learner": 0.925 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 15, "evaluationSeed": 2654435766, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 482, "rate": 0.482, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 482, "rate": 0.482, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.65, "learner": 0.65 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999568640854, "B": 0 } }, "control": { "trials": 1000, "rewards": 482, "rate": 0.482, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 945, "rate": 0.945, "pA": 0.9477746385844948, "expectedReward": 0.9477746385844948 }, "observedTrainingReward": { "control": 0.55, "learner": 0.95 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589934221465316, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 518, "rate": 0.518, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 946, "rate": 0.946, "pA": 0.053719727658153485, "expectedReward": 0.9462802723418465 }, "observedTrainingReward": { "control": 0.5375, "learner": 0.8625 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589934221465316, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 518, "rate": 0.518, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 518, "rate": 0.518, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.5, "learner": 0.5 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589934221465316, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 518, "rate": 0.518, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 946, "rate": 0.946, "pA": 0.053719727658153485, "expectedReward": 0.9462802723418465 }, "observedTrainingReward": { "control": 0.45, "learner": 0.975 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 16, "evaluationSeed": 2654435753, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 515, "rate": 0.515, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 515, "rate": 0.515, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.6, "learner": 0.6 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999998354495443, "B": 0 } }, "control": { "trials": 1000, "rewards": 515, "rate": 0.515, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 941, "rate": 0.941, "pA": 0.9477746369673554, "expectedReward": 0.9477746369673554 }, "observedTrainingReward": { "control": 0.5, "learner": 0.875 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.028147493039382028, "B": 0.9999993722898265 } }, "control": { "trials": 1000, "rewards": 485, "rate": 0.485, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 956, "rate": 0.956, "pA": 0.052633603267506324, "expectedReward": 0.9473663967324937 }, "observedTrainingReward": { "control": 0.525, "learner": 0.8 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.028147493039382028, "B": 0.9999993722898265 } }, "control": { "trials": 1000, "rewards": 485, "rate": 0.485, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 485, "rate": 0.485, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.5, "learner": 0.5 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.028147493039382028, "B": 0.9999993722898265 } }, "control": { "trials": 1000, "rewards": 485, "rate": 0.485, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 956, "rate": 0.956, "pA": 0.052633603267506324, "expectedReward": 0.9473663967324937 }, "observedTrainingReward": { "control": 0.475, "learner": 0.975 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 17, "evaluationSeed": 2654435752, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 507, "rate": 0.507, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 507, "rate": 0.507, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999654912683, "B": 0 } }, "control": { "trials": 1000, "rewards": 507, "rate": 0.507, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 944, "rate": 0.944, "pA": 0.9477746386994018, "expectedReward": 0.9477746386994018 }, "observedTrainingReward": { "control": 0.5375, "learner": 0.9625 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.02814749669973115, "B": 0.9999993722898265 } }, "control": { "trials": 1000, "rewards": 493, "rate": 0.493, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 947, "rate": 0.947, "pA": 0.05263360332517652, "expectedReward": 0.9473663966748235 }, "observedTrainingReward": { "control": 0.5875, "learner": 0.8 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.02814749669973115, "B": 0.9999993722898265 } }, "control": { "trials": 1000, "rewards": 493, "rate": 0.493, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 493, "rate": 0.493, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.5, "learner": 0.5 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.02814749669973115, "B": 0.9999993722898265 } }, "control": { "trials": 1000, "rewards": 493, "rate": 0.493, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 947, "rate": 0.947, "pA": 0.05263360332517652, "expectedReward": 0.9473663966748235 }, "observedTrainingReward": { "control": 0.475, "learner": 0.975 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 18, "evaluationSeed": 2654435755, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 468, "rate": 0.468, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 468, "rate": 0.468, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.45, "learner": 0.45 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999998946877083, "B": 0 } }, "control": { "trials": 1000, "rewards": 468, "rate": 0.468, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 937, "rate": 0.937, "pA": 0.9477746377563581, "expectedReward": 0.9477746377563581 }, "observedTrainingReward": { "control": 0.4375, "learner": 0.9 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.10737417109217877, "B": 0.9999998354495443 } }, "control": { "trials": 1000, "rewards": 532, "rate": 0.532, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 938, "rate": 0.938, "pA": 0.05422885375768486, "expectedReward": 0.9457711462423152 }, "observedTrainingReward": { "control": 0.475, "learner": 0.875 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.10737417109217877, "B": 0.9999998354495443 } }, "control": { "trials": 1000, "rewards": 532, "rate": 0.532, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 532, "rate": 0.532, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.525, "learner": 0.525 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.10737417109217877, "B": 0.9999998354495443 } }, "control": { "trials": 1000, "rewards": 532, "rate": 0.532, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 938, "rate": 0.938, "pA": 0.05422885375768486, "expectedReward": 0.9457711462423152 }, "observedTrainingReward": { "control": 0.475, "learner": 1 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 19, "evaluationSeed": 2654435754, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 496, "rate": 0.496, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 496, "rate": 0.496, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999654912683, "B": 0 } }, "control": { "trials": 1000, "rewards": 496, "rate": 0.496, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 943, "rate": 0.943, "pA": 0.9477746386994018, "expectedReward": 0.9477746386994018 }, "observedTrainingReward": { "control": 0.5625, "learner": 0.9625 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557949166241, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 938, "rate": 0.938, "pA": 0.05309197093426438, "expectedReward": 0.9469080290657356 }, "observedTrainingReward": { "control": 0.5625, "learner": 0.8375 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557949166241, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.425, "learner": 0.425 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557949166241, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 938, "rate": 0.938, "pA": 0.05309197093426438, "expectedReward": 0.9469080290657356 }, "observedTrainingReward": { "control": 0.5, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 20, "evaluationSeed": 2654435757, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 489, "rate": 0.489, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 489, "rate": 0.489, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.7, "learner": 0.7 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999326001333, "B": 0 } }, "control": { "trials": 1000, "rewards": 489, "rate": 0.489, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 961, "rate": 0.961, "pA": 0.9477746382613196, "expectedReward": 0.9477746382613196 }, "observedTrainingReward": { "control": 0.4, "learner": 0.925 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.022517996619142406, "B": 0.9999992153622831 } }, "control": { "trials": 1000, "rewards": 511, "rate": 0.511, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 956, "rate": 0.956, "pA": 0.05254638352173409, "expectedReward": 0.9474536164782659 }, "observedTrainingReward": { "control": 0.45, "learner": 0.7875 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.022517996619142406, "B": 0.9999992153622831 } }, "control": { "trials": 1000, "rewards": 511, "rate": 0.511, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 511, "rate": 0.511, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.525, "learner": 0.525 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.022517996619142406, "B": 0.9999992153622831 } }, "control": { "trials": 1000, "rewards": 511, "rate": 0.511, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 956, "rate": 0.956, "pA": 0.05254638352173409, "expectedReward": 0.9474536164782659 }, "observedTrainingReward": { "control": 0.625, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 21, "evaluationSeed": 2654435756, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 481, "rate": 0.481, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 481, "rate": 0.481, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999568640854, "B": 0 } }, "control": { "trials": 1000, "rewards": 481, "rate": 0.481, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 951, "rate": 0.951, "pA": 0.9477746385844948, "expectedReward": 0.9477746385844948 }, "observedTrainingReward": { "control": 0.475, "learner": 0.95 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 519, "rate": 0.519, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 943, "rate": 0.943, "pA": 0.05309197092549577, "expectedReward": 0.9469080290745042 }, "observedTrainingReward": { "control": 0.4375, "learner": 0.8375 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 519, "rate": 0.519, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 519, "rate": 0.519, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 519, "rate": 0.519, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 943, "rate": 0.943, "pA": 0.05309197092549577, "expectedReward": 0.9469080290745042 }, "observedTrainingReward": { "control": 0.425, "learner": 1 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 22, "evaluationSeed": 2654435759, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 524, "rate": 0.524, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 524, "rate": 0.524, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.75, "learner": 0.75 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999654912683, "B": 0 } }, "control": { "trials": 1000, "rewards": 524, "rate": 0.524, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 949, "rate": 0.949, "pA": 0.9477746386994018, "expectedReward": 0.9477746386994018 }, "observedTrainingReward": { "control": 0.5375, "learner": 0.9625 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.20971519276299447, "B": 0.9999999157501667 } }, "control": { "trials": 1000, "rewards": 476, "rate": 0.476, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 925, "rate": 0.925, "pA": 0.0577834565558161, "expectedReward": 0.9422165434441839 }, "observedTrainingReward": { "control": 0.575, "learner": 0.9125 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.20971519276299447, "B": 0.9999999157501667 } }, "control": { "trials": 1000, "rewards": 476, "rate": 0.476, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 476, "rate": 0.476, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.625, "learner": 0.625 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.20971519276299447, "B": 0.9999999157501667 } }, "control": { "trials": 1000, "rewards": 476, "rate": 0.476, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 925, "rate": 0.925, "pA": 0.0577834565558161, "expectedReward": 0.9422165434441839 }, "observedTrainingReward": { "control": 0.5, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 23, "evaluationSeed": 2654435758, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 499, "rate": 0.499, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 499, "rate": 0.499, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.5, "learner": 0.5 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999998946877083, "B": 0 } }, "control": { "trials": 1000, "rewards": 499, "rate": 0.499, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 953, "rate": 0.953, "pA": 0.9477746377563581, "expectedReward": 0.9477746377563581 }, "observedTrainingReward": { "control": 0.55, "learner": 0.9 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.02251799576543049, "B": 0.9999992153622831 } }, "control": { "trials": 1000, "rewards": 501, "rate": 0.501, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 953, "rate": 0.953, "pA": 0.05254638350872772, "expectedReward": 0.9474536164912722 }, "observedTrainingReward": { "control": 0.4375, "learner": 0.7875 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.02251799576543049, "B": 0.9999992153622831 } }, "control": { "trials": 1000, "rewards": 501, "rate": 0.501, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 501, "rate": 0.501, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.525, "learner": 0.525 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.02251799576543049, "B": 0.9999992153622831 } }, "control": { "trials": 1000, "rewards": 501, "rate": 0.501, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 953, "rate": 0.953, "pA": 0.05254638350872772, "expectedReward": 0.9474536164912722 }, "observedTrainingReward": { "control": 0.4, "learner": 0.9 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 24, "evaluationSeed": 2654435745, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.6, "learner": 0.6 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999568640854, "B": 0 } }, "control": { "trials": 1000, "rewards": 504, "rate": 0.504, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 945, "rate": 0.945, "pA": 0.9477746385844948, "expectedReward": 0.9477746385844948 }, "observedTrainingReward": { "control": 0.5625, "learner": 0.95 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.035184370571121934, "B": 0.9999994978318612 } }, "control": { "trials": 1000, "rewards": 496, "rate": 0.496, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 938, "rate": 0.938, "pA": 0.052746829397459505, "expectedReward": 0.9472531706025404 }, "observedTrainingReward": { "control": 0.5, "learner": 0.8125 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.035184370571121934, "B": 0.9999994978318612 } }, "control": { "trials": 1000, "rewards": 496, "rate": 0.496, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 496, "rate": 0.496, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.475, "learner": 0.475 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.035184370571121934, "B": 0.9999994978318612 } }, "control": { "trials": 1000, "rewards": 496, "rate": 0.496, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 938, "rate": 0.938, "pA": 0.052746829397459505, "expectedReward": 0.9472531706025404 }, "observedTrainingReward": { "control": 0.45, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 25, "evaluationSeed": 2654435744, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 483, "rate": 0.483, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 483, "rate": 0.483, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.7, "learner": 0.7 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999998946877083, "B": 0 } }, "control": { "trials": 1000, "rewards": 483, "rate": 0.483, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 946, "rate": 0.946, "pA": 0.9477746377563581, "expectedReward": 0.9477746377563581 }, "observedTrainingReward": { "control": 0.6, "learner": 0.9 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.014411517289875515, "B": 0.9999987740035673 } }, "control": { "trials": 1000, "rewards": 517, "rate": 0.517, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 940, "rate": 0.94, "pA": 0.05242582633105992, "expectedReward": 0.94757417366894 }, "observedTrainingReward": { "control": 0.525, "learner": 0.7625 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.014411517289875515, "B": 0.9999987740035673 } }, "control": { "trials": 1000, "rewards": 517, "rate": 0.517, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 517, "rate": 0.517, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.014411517289875515, "B": 0.9999987740035673 } }, "control": { "trials": 1000, "rewards": 517, "rate": 0.517, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 940, "rate": 0.94, "pA": 0.05242582633105992, "expectedReward": 0.94757417366894 }, "observedTrainingReward": { "control": 0.425, "learner": 0.95 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 26, "evaluationSeed": 2654435747, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 502, "rate": 0.502, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 502, "rate": 0.502, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.5, "learner": 0.5 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999157501667, "B": 0 } }, "control": { "trials": 1000, "rewards": 502, "rate": 0.502, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 958, "rate": 0.958, "pA": 0.9477746380368922, "expectedReward": 0.9477746380368922 }, "observedTrainingReward": { "control": 0.425, "learner": 0.9125 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.03518436912455452, "B": 0.9999994978318612 } }, "control": { "trials": 1000, "rewards": 498, "rate": 0.498, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 939, "rate": 0.939, "pA": 0.05274682937369142, "expectedReward": 0.9472531706263085 }, "observedTrainingReward": { "control": 0.5125, "learner": 0.8125 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.03518436912455452, "B": 0.9999994978318612 } }, "control": { "trials": 1000, "rewards": 498, "rate": 0.498, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 498, "rate": 0.498, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.03518436912455452, "B": 0.9999994978318612 } }, "control": { "trials": 1000, "rewards": 498, "rate": 0.498, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 939, "rate": 0.939, "pA": 0.05274682937369142, "expectedReward": 0.9472531706263085 }, "observedTrainingReward": { "control": 0.55, "learner": 0.925 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 27, "evaluationSeed": 2654435746, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 522, "rate": 0.522, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 522, "rate": 0.522, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.65, "learner": 0.65 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999568640854, "B": 0 } }, "control": { "trials": 1000, "rewards": 522, "rate": 0.522, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 947, "rate": 0.947, "pA": 0.9477746385844948, "expectedReward": 0.9477746385844948 }, "observedTrainingReward": { "control": 0.525, "learner": 0.95 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 478, "rate": 0.478, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 947, "rate": 0.947, "pA": 0.05309197092549577, "expectedReward": 0.9469080290745042 }, "observedTrainingReward": { "control": 0.4375, "learner": 0.8375 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 478, "rate": 0.478, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 478, "rate": 0.478, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.375, "learner": 0.375 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.05497557901737802, "B": 0.9999996786123911 } }, "control": { "trials": 1000, "rewards": 478, "rate": 0.478, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 947, "rate": 0.947, "pA": 0.05309197092549577, "expectedReward": 0.9469080290745042 }, "observedTrainingReward": { "control": 0.6, "learner": 0.975 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 28, "evaluationSeed": 2654435749, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 514, "rate": 0.514, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 514, "rate": 0.514, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999157501667, "B": 0 } }, "control": { "trials": 1000, "rewards": 514, "rate": 0.514, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 958, "rate": 0.958, "pA": 0.9477746380368922, "expectedReward": 0.9477746380368922 }, "observedTrainingReward": { "control": 0.4875, "learner": 0.9125 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947094639555, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 486, "rate": 0.486, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 940, "rate": 0.94, "pA": 0.05335676067718549, "expectedReward": 0.9466432393228145 }, "observedTrainingReward": { "control": 0.5, "learner": 0.85 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947094639555, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 486, "rate": 0.486, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 486, "rate": 0.486, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.475, "learner": 0.475 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.06871947094639555, "B": 0.9999997428899129 } }, "control": { "trials": 1000, "rewards": 486, "rate": 0.486, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 940, "rate": 0.94, "pA": 0.05335676067718549, "expectedReward": 0.9466432393228145 }, "observedTrainingReward": { "control": 0.475, "learner": 0.975 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 29, "evaluationSeed": 2654435748, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 507, "rate": 0.507, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 507, "rate": 0.507, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.75, "learner": 0.75 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999568640854, "B": 0 } }, "control": { "trials": 1000, "rewards": 507, "rate": 0.507, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 941, "rate": 0.941, "pA": 0.9477746385844948, "expectedReward": 0.9477746385844948 }, "observedTrainingReward": { "control": 0.475, "learner": 0.95 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589934221465316, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 493, "rate": 0.493, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 949, "rate": 0.949, "pA": 0.053719727658153485, "expectedReward": 0.9462802723418465 }, "observedTrainingReward": { "control": 0.4375, "learner": 0.8625 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589934221465316, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 493, "rate": 0.493, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 493, "rate": 0.493, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.5, "learner": 0.5 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.08589934221465316, "B": 0.9999997943119303 } }, "control": { "trials": 1000, "rewards": 493, "rate": 0.493, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 949, "rate": 0.949, "pA": 0.053719727658153485, "expectedReward": 0.9462802723418465 }, "observedTrainingReward": { "control": 0.55, "learner": 0.925 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } }, { "seed": 30, "evaluationSeed": 2654435751, "phases": { "baseline": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0, "B": 0 } }, "control": { "trials": 1000, "rewards": 508, "rate": 0.508, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 508, "rate": 0.508, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.55, "learner": 0.55 } }, "acquisition": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.9999999654912683, "B": 0 } }, "control": { "trials": 1000, "rewards": 508, "rate": 0.508, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 949, "rate": 0.949, "pA": 0.9477746386994018, "expectedReward": 0.9477746386994018 }, "observedTrainingReward": { "control": 0.5375, "learner": 0.9625 } }, "reversal": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.10737417869465316, "B": 0.9999998354495443 } }, "control": { "trials": 1000, "rewards": 492, "rate": 0.492, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 940, "rate": 0.94, "pA": 0.054228853949677004, "expectedReward": 0.945771146050323 }, "observedTrainingReward": { "control": 0.45, "learner": 0.875 } }, "disconnect": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.10737417869465316, "B": 0.9999998354495443 } }, "control": { "trials": 1000, "rewards": 492, "rate": 0.492, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 492, "rate": 0.492, "pA": 0.5, "expectedReward": 0.5 }, "observedTrainingReward": { "control": 0.45, "learner": 0.45 } }, "restore": { "values": { "control": { "A": 0, "B": 0 }, "learner": { "A": 0.10737417869465316, "B": 0.9999998354495443 } }, "control": { "trials": 1000, "rewards": 492, "rate": 0.492, "pA": 0.5, "expectedReward": 0.5 }, "learner": { "trials": 1000, "rewards": 940, "rate": 0.94, "pA": 0.054228853949677004, "expectedReward": 0.945771146050323 }, "observedTrainingReward": { "control": 0.425, "learner": 0.975 } } }, "checks": { "acquisition": true, "reversal": true, "disconnect": true, "restore": true, "preservedMemory": true, "frozenControl": true } } ], "limits": [ "Hand-designed toy environment with deterministic rewards; no body physics or neural spikes.", "The disconnect intervention removes all learned choice bias by construction.", "No claim about biological memory, MN9 or the earlier 466-neuron candidate.", "Thirty seeds test this protocol only, not robustness to arbitrary environments." ] }