{"id":"W2885541157","doi":"10.1109/tac.2020.2978037","title":"On Passivity, Reinforcement Learning, and Higher Order Learning in Multiagent Finite Games","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Convergence (economics); Monotonic function; Nash equilibrium; Stochastic game; Property (philosophy); Class (philosophy); Exploit","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":[],"category_scores_codex":[0.0002814618,0.0002993009,0.0003722203,0.0002283857,0.0002336177,0.0002146007,0.0003414505,0.0001047433,0.0003752672],"category_scores_gemma":[0.0001294288,0.0002851259,0.00009279706,0.0004823126,0.00005730538,0.0002737487,0.000009315008,0.000686726,0.0002256963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000981807,"about_ca_system_score_gemma":0.00006432545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002164654,"about_ca_topic_score_gemma":0.000005162521,"domain_scores_codex":[0.9977937,0.0002640907,0.0005098646,0.0004868117,0.0005264327,0.0004190685],"domain_scores_gemma":[0.9984085,0.0008587104,0.0001985443,0.0002816614,0.00005737467,0.0001951957],"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":[0.00002561194,0.00005339128,0.00009326361,0.00004253025,0.00005364593,0.00001851929,0.001024589,0.9501436,0.0001568179,0.0003625732,0.00004768097,0.04797778],"study_design_scores_gemma":[0.002779205,0.0008405565,0.0008893826,0.0001001224,0.00002722488,0.000002069484,0.00004066938,0.9927779,0.0002382671,0.00002236387,0.001996798,0.0002854778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00324304,0.00001850542,0.9905873,0.003888797,0.0002944797,0.0005112668,5.683958e-7,0.0005665259,0.0008895106],"genre_scores_gemma":[0.9937051,0.00002873413,0.00265098,0.001733563,0.00002339468,0.00008882175,9.230652e-7,0.00002675562,0.001741746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9904621,"threshold_uncertainty_score":0.9999601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01571176188537983,"score_gpt":0.2457269065098175,"score_spread":0.2300151446244377,"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."}}