{"id":"W3012442074","doi":"10.1109/cdc40024.2019.9029788","title":"Q-Learning with Side Information in Multi-Agent Finite Games","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Human–computer interaction","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002029751,0.00009347058,0.00009688421,0.0001607293,0.00003162722,0.0001791595,0.0003395577,0.00003492954,0.00005045543],"category_scores_gemma":[0.00006639049,0.0000731964,0.00001819262,0.0002888935,0.00001096584,0.001456727,0.000144735,0.0001931904,0.001110317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004434936,"about_ca_system_score_gemma":0.00003962898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003972598,"about_ca_topic_score_gemma":0.000007047809,"domain_scores_codex":[0.9991654,0.00003457328,0.0002089025,0.0001303171,0.0002491551,0.0002116155],"domain_scores_gemma":[0.9994462,0.00009382742,0.00009920882,0.0002742534,0.00004820737,0.00003833288],"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":[0.000002708346,0.000005219422,0.03250046,0.00001085047,0.000003421572,0.00000150933,0.001245384,0.9613589,0.00001871493,0.001747814,0.00001681584,0.003088172],"study_design_scores_gemma":[0.000545176,0.0001470825,0.01943863,0.00002940719,8.294186e-7,0.000002187865,0.0002015413,0.9734162,0.0001472177,0.000005741471,0.005944236,0.0001217326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03283464,0.000003018962,0.9518789,0.0001350563,0.0000942273,0.0001748561,3.930371e-8,0.0001466317,0.01473265],"genre_scores_gemma":[0.9063522,0.000004974321,0.08904721,0.0003603789,0.000004069991,0.000005571611,0.000003623018,0.000004301631,0.004217656],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8735176,"threshold_uncertainty_score":0.9996674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01350555464671978,"score_gpt":0.2289392024984458,"score_spread":0.215433647851726,"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."}}