{"id":"W4244090038","doi":"10.1007/978-1-4471-7452-3_17","title":"Reinforcement Learning","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Error-driven learning; Formalism (music); Artificial intelligence; Psychology; 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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002301299,0.0003967864,0.0003689517,0.0002195161,0.0001062345,0.0002500232,0.001370852,0.0003019111,0.001943706],"category_scores_gemma":[0.00002686427,0.0003738684,0.0001918507,0.00003699294,0.00003617885,0.0002950315,0.0009089526,0.0008265647,0.01112765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001429093,"about_ca_system_score_gemma":0.0001898704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004112749,"about_ca_topic_score_gemma":4.497925e-7,"domain_scores_codex":[0.9978575,0.0000126166,0.0004588819,0.000558874,0.000742305,0.0003698413],"domain_scores_gemma":[0.9981821,0.00009990587,0.0003632505,0.001135389,0.000115429,0.0001039094],"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":[7.107864e-7,5.832121e-7,0.000003581217,0.00001815172,0.00003089328,0.000006292249,0.00003301021,0.4221015,0.000002053334,0.5730885,0.002890773,0.001824006],"study_design_scores_gemma":[0.0001405643,0.0001614147,0.000002057136,0.00008599095,0.00001147039,0.000006754224,0.000001660329,0.2895986,0.0000153833,0.001201334,0.7083657,0.0004089942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[4.232158e-8,0.0000324068,0.488828,0.00008702543,0.000392169,0.0001541329,4.90835e-8,0.0002640683,0.5102421],"genre_scores_gemma":[0.0009669383,0.0001187026,0.00915066,0.0004801129,0.0001070772,0.000002408178,0.00002111838,0.00005086236,0.9891021],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.705475,"threshold_uncertainty_score":0.9998713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01983590515921726,"score_gpt":0.2269463777335071,"score_spread":0.2071104725742899,"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."}}