{"id":"W3197039934","doi":"10.1016/j.tins.2021.07.007","title":"Learning offline: memory replay in biological and artificial reinforcement learning","year":2021,"lang":"en","type":"review","venue":"Trends in Neurosciences","topic":"Memory and Neural Mechanisms","field":"Neuroscience","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec; Fonds de recherche du Québec – Nature et technologies; Leverhulme Trust; Natural Sciences and Engineering Research Council of Canada; Wellcome Trust","keywords":"Reinforcement learning; Memory consolidation; Artificial intelligence; Computer science; Cognitive science; Artificial neural network; Process (computing); Key (lock); Psychology; Neuroscience","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001361706,0.0005008905,0.001346944,0.0009469747,0.0003211118,0.0001919944,0.0005884506,0.0002736418,0.0002979531],"category_scores_gemma":[0.003662989,0.0003808906,0.0002011746,0.002642264,0.0003963676,0.0002368405,0.0004464549,0.001645563,0.0000208996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005113129,"about_ca_system_score_gemma":0.00009638876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004692795,"about_ca_topic_score_gemma":0.000012316,"domain_scores_codex":[0.9939018,0.002160426,0.001036432,0.001702047,0.0004970644,0.000702164],"domain_scores_gemma":[0.9979104,0.001205176,0.0004412071,0.0002924828,0.00001045788,0.0001402464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001049099,0.00006481129,0.00002370647,0.0002857312,8.381045e-7,0.0006964749,0.0001281572,0.0006073781,0.006174061,0.0003106089,0.000007387378,0.9916903],"study_design_scores_gemma":[0.001095481,0.004346962,0.0001093687,0.0130076,0.0001469034,0.001862297,0.0007063122,0.01069404,0.04588453,0.0004040936,0.9178298,0.003912619],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.04971172,0.9391903,0.00002339032,0.0001421428,0.004324667,0.0007813616,0.000007728,0.0002140663,0.005604675],"genre_scores_gemma":[0.02623121,0.9695586,0.00002153746,0.0001216814,0.0001045703,0.0000642403,0.00000997795,0.00002605958,0.003862093],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9877777,"threshold_uncertainty_score":0.9998643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3170894236952891,"score_gpt":0.4203491862720325,"score_spread":0.1032597625767434,"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."}}