{"id":"W4411225534","doi":"10.1017/9781009504942.008","title":"Reinforcement learning","year":2025,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Waterloo; McMaster University","funders":"","keywords":"Reinforcement; Reinforcement learning; Psychology; Computer science; Artificial intelligence; Social psychology","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":[0.0009740457,0.001087738,0.000821661,0.0004031,0.000401485,0.001521167,0.001356913,0.001171803,0.01870276],"category_scores_gemma":[0.00387563,0.0002746905,0.0005276828,0.0004921579,0.001183789,0.001460565,0.001172797,0.001833225,0.003931502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001083344,"about_ca_system_score_gemma":0.001032351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001142707,"about_ca_topic_score_gemma":0.001437783,"domain_scores_codex":[0.9993568,0.0002422068,0.00003552709,0.0001383075,0.0001814521,0.00004573747],"domain_scores_gemma":[0.9989785,0.0006772007,0.00005226842,0.00009855881,0.0001342269,0.00005930101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006303934,0.0001172043,0.0005472106,0.0004513798,0.00008316997,0.00009872355,0.0001103827,0.1656809,0.001153075,0.6063812,0.02592192,0.1993918],"study_design_scores_gemma":[0.00005627818,0.0000952078,0.00022577,0.0001694852,0.00002847609,0.0001220691,0.00005170329,0.3029223,0.0008820318,0.5864353,0.1089796,0.00003170031],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.003726223,0.005667092,0.9003602,0.002695367,0.0006986959,0.0001419628,0.0002612346,0.000683782,0.0857655],"genre_scores_gemma":[0.4204924,0.01802304,0.4173431,0.002668892,0.001149706,0.001181832,0.001308965,0.0004530725,0.1373791],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01870276,"threshold_uncertainty_score":0.062567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0182280915149218,"score_gpt":0.2018063437256893,"score_spread":0.1835782522107675,"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."}}