{"id":"W4385791672","doi":"10.1017/9781009258227.018","title":"Reinforcement Learning","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Code (set theory); Reinforcement learning; Implementation; Artificial intelligence; Software engineering; Programming language","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":[0.0002132315,0.0004602661,0.0004134981,0.0003675256,0.0003650798,0.0001920926,0.001902107,0.0003718145,0.000004967153],"category_scores_gemma":[0.00003015851,0.0005741868,0.0002644486,0.00002624078,0.0001380774,0.0002345822,0.002037652,0.001011696,0.0003618964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003067334,"about_ca_system_score_gemma":0.0001545214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004240809,"about_ca_topic_score_gemma":2.871921e-7,"domain_scores_codex":[0.9977621,0.00004519873,0.0003060228,0.0007180468,0.0006730067,0.0004955978],"domain_scores_gemma":[0.9979794,0.0001350126,0.0004161046,0.001069408,0.000186274,0.000213775],"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":[0.000008818396,0.000001217104,8.473967e-7,0.0000536023,0.0001154327,0.0003304329,0.0000619454,0.08142462,0.000006857847,0.8992195,0.01794002,0.0008366802],"study_design_scores_gemma":[0.000360632,0.0001133669,0.000003650805,0.000179898,0.00006646642,0.000009365604,0.00001132612,0.07557493,0.00005985169,0.00001065906,0.9230297,0.000580131],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[6.441454e-7,0.00001151706,0.3473187,0.00001810652,0.000409437,0.0002323323,0.000002483426,0.0007755655,0.6512312],"genre_scores_gemma":[0.0003523767,0.0001330158,0.0008165797,0.0000665623,0.0001074453,8.116368e-7,0.00004193782,0.00006907935,0.9984122],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9050897,"threshold_uncertainty_score":0.999671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03100131681971751,"score_gpt":0.2074911771978943,"score_spread":0.1764898603781768,"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."}}