{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001602345,0.0004576376,0.0004260395,0.0003713248,0.0003601871,0.0001835981,0.001961875,0.0003748809,0.000006499407],"category_scores_gemma":[0.00002823884,0.0005726983,0.0002621259,0.00002170983,0.0001291934,0.0002199512,0.002010455,0.001005662,0.00005772118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000386032,"about_ca_system_score_gemma":0.0002601937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004023209,"about_ca_topic_score_gemma":1.91217e-7,"domain_scores_codex":[0.9980087,0.0000480747,0.0003030995,0.0006942856,0.0005218787,0.0004239751],"domain_scores_gemma":[0.9980142,0.0001206469,0.0003780233,0.001103991,0.0002169944,0.0001661251],"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":[0.00001166853,0.000001779636,9.402425e-7,0.00007886752,0.0001286981,0.0001519467,0.00003892148,0.04200697,0.000004979052,0.9219901,0.03377934,0.00180579],"study_design_scores_gemma":[0.0003764113,0.00008500784,0.000001566476,0.000258885,0.00008478505,0.000005857046,0.000006624393,0.06631155,0.00008823236,0.000006363798,0.9322852,0.000489547],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[2.453852e-7,0.00003212638,0.4345303,0.00001813122,0.0002786981,0.0002131652,0.000001978355,0.0003047386,0.5646206],"genre_scores_gemma":[0.0003433299,0.0001189656,0.001796191,0.0001320407,0.00006784087,6.807252e-7,0.00003235141,0.00002701071,0.9974816],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9219837,"threshold_uncertainty_score":0.9996725,"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."}}