{"id":"W4285255083","doi":"10.1007/978-3-031-79167-3_2","title":"Reinforcement Learning Theory","year":2022,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on artificial intelligence and machine learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Canadian Institute for Advanced Research","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Plan (archaeology); Context (archaeology); Cognitive science; Artificial intelligence; Psychology; Social psychology; History","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","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001485698,0.0007933967,0.0006986815,0.0006642623,0.001419708,0.0004844072,0.001225566,0.0003317415,0.005774932],"category_scores_gemma":[0.001311262,0.0007610465,0.0003066263,0.00015723,0.0001957261,0.0002571533,0.0009294393,0.003425729,0.00056272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001975716,"about_ca_system_score_gemma":0.0001113865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004490072,"about_ca_topic_score_gemma":0.000009729972,"domain_scores_codex":[0.9958655,0.0004099088,0.000872353,0.001139964,0.001037353,0.0006749509],"domain_scores_gemma":[0.9962017,0.002061094,0.0007003415,0.0007480432,0.00008757147,0.0002012748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004011289,0.000006761147,0.000002708287,0.00002293509,0.00007071978,0.00002597773,0.0003789987,0.4432053,0.00001855186,0.3914792,0.00003144486,0.1647173],"study_design_scores_gemma":[0.00003955812,0.001099656,0.000003115296,0.0002822579,0.0001233956,0.0000374629,0.0001041358,0.3952208,0.002135539,0.07133807,0.5282778,0.001338238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.000005134227,0.0004871864,0.6211156,0.0004927206,0.0003854955,0.0003143254,0.000001410414,0.0004262876,0.3767719],"genre_scores_gemma":[0.4125758,0.004721509,0.003188477,0.001786364,0.0006417387,0.0001477763,0.00009831593,0.00036529,0.5764747],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.6179271,"threshold_uncertainty_score":0.9998803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04072940189197726,"score_gpt":0.2609339799200801,"score_spread":0.2202045780281028,"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."}}