{"id":"W4310613925","doi":"10.1002/9781119808602.ch3","title":"Reinforcement Learning","year":2022,"lang":"en","type":"other","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Markov decision process; Dynamic programming; Optimal control; Mathematical proof; Computer science; Bellman equation; Mathematical optimization; Class (philosophy); Stochastic control; Control (management); Field (mathematics); Markov process; Mathematics; Artificial intelligence","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001287627,0.0001459378,0.0001508178,0.0001634469,0.00006110845,0.00005969846,0.0009913045,0.00005746532,0.01371026],"category_scores_gemma":[0.00001937704,0.0001373974,0.00006202855,0.000148778,0.00001563048,0.00004010226,0.0007496803,0.0002788754,0.000363116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008869517,"about_ca_system_score_gemma":0.0000473716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001236527,"about_ca_topic_score_gemma":0.00001506665,"domain_scores_codex":[0.9990095,0.00004692594,0.0001031522,0.0003261907,0.0002929031,0.0002212938],"domain_scores_gemma":[0.9993134,0.00002189128,0.0001222593,0.0004902041,0.000008268647,0.00004403405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[7.234685e-7,0.00001177806,0.00002733511,0.000008826082,0.0000658531,0.00002747788,0.00005624073,0.0006245389,0.000001557151,0.2536144,0.6723215,0.07323975],"study_design_scores_gemma":[0.0001208772,0.00005248106,0.000001577555,0.000005059483,0.0000031738,0.000002514085,0.000008169451,0.06701202,2.579534e-7,0.00008734972,0.9325503,0.0001562971],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[9.213426e-9,0.00009080883,0.4878463,0.0000752249,0.0001497836,0.0001051251,1.274121e-7,0.0007077393,0.5110249],"genre_scores_gemma":[0.0002855639,0.00001007013,0.02664739,0.0002637052,0.00006485444,0.00005562207,0.0000118335,0.0001281289,0.9725328],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4615079,"threshold_uncertainty_score":0.9871913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00743149318627673,"score_gpt":0.2207259863854765,"score_spread":0.2132944931991998,"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."}}