{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00453212,0.001607204,0.001256049,0.0008924102,0.000577748,0.001581156,0.001579438,0.001417225,0.003220362],"category_scores_gemma":[0.0117925,0.0005990372,0.001737119,0.0004900823,0.004351465,0.002299678,0.002288607,0.002993115,0.0004243924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002216477,"about_ca_system_score_gemma":0.001729184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002729123,"about_ca_topic_score_gemma":0.001550947,"domain_scores_codex":[0.9981502,0.0008688468,0.00011337,0.0002776372,0.0004077133,0.0001822857],"domain_scores_gemma":[0.9927503,0.005452305,0.0005216072,0.0004223838,0.0005675124,0.0002858873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005075273,0.00005346251,0.0002868477,0.0001547278,0.00007531101,0.0001282736,0.0002100479,0.3907767,0.003315719,0.5924007,0.0004155796,0.01213187],"study_design_scores_gemma":[0.00002313146,0.000122732,0.0001038166,0.00004082768,0.00002008054,0.00003627651,0.00001305298,0.7402132,0.001087602,0.2568842,0.00143465,0.00002047507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005781117,0.0002282461,0.9892907,0.0001890473,0.00003532655,0.00004455519,0.0000161863,0.00005561136,0.004359234],"genre_scores_gemma":[0.8148684,0.001305439,0.1734592,0.0003709655,0.0001984759,0.0006322064,0.00008543183,0.0001352925,0.008944636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00453212,"threshold_uncertainty_score":0.0239684,"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."}}