{"id":"W2913966743","doi":"10.1109/cdc.2018.8619157","title":"On Passivity and Reinforcement Learning in Finite Games","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Passivity; Reinforcement learning; Convergence (economics); Monotonic function; Stochastic game; Computer science; Property (philosophy); Class (philosophy); Exploit; Reinforcement; Mathematical optimization; Scheme (mathematics); Artificial intelligence; Mathematics; Mathematical economics; Engineering; Economics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003100791,0.0001038741,0.0001033611,0.0001335227,0.00009754545,0.0001323597,0.0002782302,0.00004069941,0.00007791791],"category_scores_gemma":[0.0002387691,0.00008947145,0.00001693407,0.0002227607,0.00006497522,0.0002655778,0.0002645129,0.0001853679,0.0001571185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003567902,"about_ca_system_score_gemma":0.00002387921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002787686,"about_ca_topic_score_gemma":0.00000956545,"domain_scores_codex":[0.9990404,0.00005019096,0.0001781315,0.0002561683,0.000226378,0.00024878],"domain_scores_gemma":[0.9993322,0.0002242685,0.00006412797,0.00028646,0.0000352872,0.00005768853],"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":[0.000008307043,0.00001144238,0.006134047,0.000007929842,0.000006074544,0.000006873279,0.0007938813,0.868403,0.00006303509,0.1087959,0.0005129193,0.01525667],"study_design_scores_gemma":[0.0003037955,0.0004904846,0.007065823,0.00003023075,9.151771e-7,0.000001447198,0.00001990211,0.9854684,0.0005214897,0.000495847,0.005470268,0.0001314144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01374706,0.00000473286,0.9364775,0.0004873314,0.0001287858,0.00008838617,1.546941e-8,0.0001329899,0.04893322],"genre_scores_gemma":[0.9849105,0.00001165343,0.007542743,0.0006880549,0.00003170175,0.000004652587,5.735085e-7,0.000005075123,0.00680506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9711635,"threshold_uncertainty_score":0.364854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01490182372364465,"score_gpt":0.2495275137318254,"score_spread":0.2346256900081808,"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."}}