{"id":"W2904676870","doi":"10.7554/elife.32548","title":"Offline replay supports planning in human reinforcement learning","year":2018,"lang":"en","type":"article","venue":"eLife","topic":"Memory and Neural Mechanisms","field":"Neuroscience","cited_by":154,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Institute of Mental Health; John Templeton Foundation","keywords":"Reinforcement learning; Task (project management); Computer science; Artificial intelligence; Machine learning; Human–computer interaction","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007094118,0.0003067591,0.0002597472,0.0002051624,0.0001839855,0.0009664292,0.0004971386,0.0003531777,0.001689485],"category_scores_gemma":[0.004879044,0.000438277,0.0002976544,0.0001449275,0.0007605467,0.001445839,0.0007465265,0.0007193818,0.0002285771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004333109,"about_ca_system_score_gemma":0.000433055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001515702,"about_ca_topic_score_gemma":0.0014447,"domain_scores_codex":[0.9996929,0.0001025043,0.00002062463,0.0001037054,0.00004264977,0.00003762444],"domain_scores_gemma":[0.9989375,0.0004579983,0.0002139311,0.0002312251,0.00008037978,0.0000789286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002553145,0.0004602903,0.04448607,0.0003892118,0.0004378932,0.0007543828,0.002380912,0.1932027,0.3276981,0.02958564,0.001631074,0.3964207],"study_design_scores_gemma":[0.0001567179,0.001323431,0.1271215,0.00008373265,0.0001998019,0.0007504633,0.0005930746,0.5903601,0.1208594,0.154393,0.003996831,0.0001618785],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8200815,0.0003305634,0.1741625,0.0004115089,0.00002895845,0.0000306759,0.0001336941,0.0005665673,0.004254096],"genre_scores_gemma":[0.9874001,0.00006827997,0.01197476,0.0000194066,0.000004554918,0.0000141054,0.00004619692,0.00003411549,0.0004385032],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001689485,"threshold_uncertainty_score":0.005651891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1017343992395071,"score_gpt":0.3625170537246353,"score_spread":0.2607826544851282,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}