{"id":"W4392123244","doi":"10.1007/978-3-031-52554-4_1","title":"Reinforcement Learning Background","year":2024,"lang":"en","type":"book-chapter","venue":"SpringerBriefs in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Memorial University of Newfoundland","funders":"","keywords":"Reinforcement learning; Reinforcement; Psychology; Computer science; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004474267,0.0009862116,0.0007215174,0.000648728,0.0005586362,0.002234779,0.001488382,0.001391425,0.05143235],"category_scores_gemma":[0.001743298,0.0003937542,0.0005206964,0.001206471,0.0009644952,0.002136619,0.0009672011,0.002613101,0.01729107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001575778,"about_ca_system_score_gemma":0.001167327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003089454,"about_ca_topic_score_gemma":0.002177713,"domain_scores_codex":[0.9996563,0.0000633942,0.00001462981,0.0001181681,0.0001158336,0.00003161708],"domain_scores_gemma":[0.999378,0.0003379249,0.00002671643,0.00007572625,0.0001319615,0.00004967523],"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":[0.00002587626,0.0001169427,0.0001366735,0.0004829411,0.00001699382,0.00006679741,0.00008496732,0.01729133,0.000595331,0.6116753,0.06366051,0.3058463],"study_design_scores_gemma":[0.00001270919,0.0000478548,0.0002016054,0.0002887034,0.00001477865,0.0001299971,0.00002691286,0.03074083,0.0007822186,0.4532534,0.5144795,0.00002136499],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.002063165,0.05107676,0.3494399,0.005748543,0.002191026,0.00008911022,0.0006414694,0.001097551,0.5876524],"genre_scores_gemma":[0.1568212,0.07212338,0.1441459,0.003596487,0.004435873,0.0003707963,0.001386627,0.0008102931,0.6163095],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.05143235,"threshold_uncertainty_score":0.1720583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02602594229317956,"score_gpt":0.2586378559370339,"score_spread":0.2326119136438543,"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."}}