{"id":"W4243101510","doi":"10.1002/9781118445112.stat08000","title":"Reinforcement Learning","year":2017,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Reinforcement learning; Computer science; A priori and a posteriori; Sequence (biology); Artificial intelligence; Quality (philosophy); Reinforcement; Machine learning; 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":[0.001336604,0.001035719,0.001007675,0.0004908635,0.0003548751,0.00172318,0.001465279,0.00102935,0.01579251],"category_scores_gemma":[0.006806139,0.0002360775,0.0005190938,0.0005338096,0.001331566,0.00143665,0.001363124,0.001975681,0.003351572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001082351,"about_ca_system_score_gemma":0.001383896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001657622,"about_ca_topic_score_gemma":0.001289008,"domain_scores_codex":[0.998672,0.0005106701,0.00006816159,0.0003196804,0.0003379549,0.00009144806],"domain_scores_gemma":[0.9975503,0.001479803,0.0001700473,0.0002480981,0.0004036373,0.000148175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001561081,0.0001838033,0.001342835,0.0005188101,0.0001374683,0.0001560544,0.0001019621,0.3272126,0.001578607,0.3584188,0.03241745,0.2777754],"study_design_scores_gemma":[0.00007729536,0.0001160122,0.0003478127,0.0001618455,0.00003808145,0.0001076556,0.00003455076,0.6579032,0.001047776,0.2947643,0.04536761,0.00003386956],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00728935,0.004483426,0.9266406,0.003061377,0.0005270247,0.0001550088,0.0002798697,0.001082762,0.05648055],"genre_scores_gemma":[0.7091284,0.007607078,0.2181084,0.002074705,0.001025545,0.0006412488,0.001221143,0.0004201432,0.05977332],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01579251,"threshold_uncertainty_score":0.05283123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04106047788657132,"score_gpt":0.3130910355740826,"score_spread":0.2720305576875113,"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."}}