{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001869987,0.000748598,0.000628828,0.001492378,0.0003704672,0.002069392,0.005044467,0.0003035032,0.0001470621],"category_scores_gemma":[0.00003774422,0.0007819638,0.0002284518,0.0008065813,0.0007386749,0.00132291,0.005372089,0.002002595,0.001819593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001001109,"about_ca_system_score_gemma":0.0007058099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002358973,"about_ca_topic_score_gemma":0.000005534085,"domain_scores_codex":[0.9936343,0.00002287949,0.001031664,0.002082306,0.00207535,0.0011535],"domain_scores_gemma":[0.9969462,0.0001721029,0.0004066377,0.001926695,0.0002391075,0.0003092773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001322038,0.000003862132,0.00001016816,0.0000665575,0.0000153247,0.0001446913,0.0002348168,0.47076,0.00001412098,0.5169913,0.00009506342,0.01166271],"study_design_scores_gemma":[0.0001885852,0.0002211998,0.00004383897,0.0007795667,0.00001208542,0.000049281,0.000002077058,0.8716282,0.00007110373,0.01177031,0.114366,0.0008677229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00001286142,0.0002028045,0.65724,0.000195783,0.002946745,0.0002813239,2.268841e-7,0.0004595176,0.3386607],"genre_scores_gemma":[0.0587446,0.0004774131,0.1495966,0.0009858321,0.001344337,0.0000342999,0.00001078842,0.0002132329,0.7885929],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5076434,"threshold_uncertainty_score":0.9994631,"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."}}