{"id":"W4399828205","doi":"10.1007/978-3-031-54071-4_21","title":"Reinforcement Learning for Fully Observable Models: Convergence to Near Optimality under Weak Feller Continuity","year":2024,"lang":"en","type":"book-chapter","venue":"Systems & control","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Observable; Reinforcement learning; Convergence (economics); Reinforcement; Computer science; Mathematics; Mathematical optimization; Artificial intelligence; Psychology; Economics; Physics; 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":[0.001768663,0.0009509522,0.001434504,0.0002410443,0.0004733992,0.001469417,0.00193095,0.000613287,0.0001137058],"category_scores_gemma":[0.0001004784,0.0009367169,0.0005746553,0.0001463918,0.0001106214,0.0006165334,0.0006898663,0.001019776,0.001279332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006603203,"about_ca_system_score_gemma":0.0005219656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002602176,"about_ca_topic_score_gemma":0.0000132111,"domain_scores_codex":[0.9943544,0.0001015737,0.001600524,0.001545879,0.00128795,0.001109708],"domain_scores_gemma":[0.9957948,0.0004426214,0.0008115174,0.001680312,0.0008216332,0.0004490616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003709975,0.000003702206,0.00000484903,0.0003200187,0.0002754617,0.000008128967,0.0001947699,0.5709583,0.00001456691,0.4249898,0.003077843,0.0001154948],"study_design_scores_gemma":[0.0007621445,0.000329129,0.000003311689,0.0006064234,0.0001254488,0.000008954597,0.00003295487,0.6744193,0.00000243271,0.002832348,0.3201964,0.000681063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.000003395555,0.001050786,0.7803041,0.0004068262,0.003296861,0.003400516,0.00001167253,0.0005705495,0.2109552],"genre_scores_gemma":[0.2024267,0.00004690098,0.003089878,0.0004633436,0.0004588534,0.0004343046,0.00004391496,0.0001581634,0.792878],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7772143,"threshold_uncertainty_score":0.9995672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04009775781671515,"score_gpt":0.2557781574063045,"score_spread":0.2156803995895893,"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."}}