{"id":"W3176726161","doi":"10.1038/s41539-021-00098-4","title":"A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments","year":2021,"lang":"en","type":"article","venue":"npj Science of Learning","topic":"Evolutionary Game Theory and Cooperation","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Calmness; Reinforcement; Reinforcement learning; Cognitive psychology; Psychology; Computer science; Social psychology; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.001328036,0.0000775584,0.0001495514,0.0001352855,0.0004870624,0.00004901967,0.0001891416,0.00005957554,0.0001751485],"category_scores_gemma":[0.0005486944,0.00007939808,0.00002596859,0.0006734947,0.0008435125,0.0007201777,0.0000973372,0.0001673657,0.000001447016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192235,"about_ca_system_score_gemma":0.0003756371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001865692,"about_ca_topic_score_gemma":0.0001487372,"domain_scores_codex":[0.9985613,0.0001744205,0.000254082,0.0002429421,0.0005227546,0.0002445664],"domain_scores_gemma":[0.9995182,0.00006182975,0.0001753233,0.00009957507,0.00008512474,0.00005992584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0000369499,0.00002075506,0.07982755,0.00002246058,0.000007521647,0.000003592138,0.03229667,0.05653305,0.8033116,0.0141744,0.000001345145,0.01376407],"study_design_scores_gemma":[0.001559315,0.0003513752,0.5057992,0.0002751649,0.00004279609,0.00001733092,0.1099308,0.006479863,0.3666864,0.004105125,0.004117032,0.0006354984],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966809,0.0002201497,0.0003269081,0.00009325797,0.00007339531,0.00008580396,4.224727e-7,0.000009198642,0.002509934],"genre_scores_gemma":[0.9978909,0.0002248167,0.0007339411,0.00001281065,0.00002170121,0.000002444373,0.000003358177,0.000003947445,0.001106053],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4366252,"threshold_uncertainty_score":0.3746139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009214760714353955,"score_gpt":0.2580420128277638,"score_spread":0.2488272521134098,"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."}}