{"id":"W3119430014","doi":"10.65109/bwtd6573","title":"Partially Observable Mean Field Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Scalability; Field (mathematics); Visibility; Artificial intelligence; Observable; Mathematical optimization; Set (abstract data type); Q-learning; Machine learning; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0006065843,0.0004336994,0.0004876178,0.0001270974,0.0002271433,0.00146013,0.002263511,0.0003868305,0.0007663902],"category_scores_gemma":[0.0003058395,0.0004396125,0.0002750318,0.0002665861,0.0000254159,0.0004491127,0.006255826,0.001613155,0.0001653371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001445154,"about_ca_system_score_gemma":0.0004913425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003055754,"about_ca_topic_score_gemma":0.00004087904,"domain_scores_codex":[0.9966111,0.0001679471,0.0007247555,0.0009507975,0.000885438,0.0006599927],"domain_scores_gemma":[0.9970717,0.0002213344,0.0003964972,0.001845574,0.0002728661,0.0001919624],"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":[0.000002503424,0.00001216812,0.0005161515,0.0001007058,0.00008239926,0.00004378608,0.0009222799,0.9855374,0.00006441755,0.009231206,0.001598247,0.001888711],"study_design_scores_gemma":[0.0001913677,0.0001568926,0.00009340941,0.0002038057,0.00002341694,0.000005546986,0.0001148688,0.9811945,0.003574927,0.0001895195,0.01369504,0.0005567314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007617536,0.0001044085,0.9355256,0.001206399,0.001677034,0.0003035944,7.35744e-8,0.0006694786,0.05975167],"genre_scores_gemma":[0.7636154,0.0002772615,0.1744128,0.002675423,0.0002871252,0.00007939186,0.00008850572,0.0000508412,0.05851331],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7628536,"threshold_uncertainty_score":0.9998056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03734177779240893,"score_gpt":0.2667191034409659,"score_spread":0.229377325648557,"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."}}