{"id":"W3206893708","doi":"","title":"An Independent Learning Algorithm for a Class of Symmetric Stochastic Games","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Class (philosophy); Property (philosophy); Reinforcement learning; Mathematical economics; Computer science; Action (physics); Symmetry (geometry); Zero (linguistics); Mathematics; Mathematical optimization; Artificial intelligence; Discrete 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"],"consensus_categories":[],"category_scores_codex":[0.0004557426,0.0003360163,0.0005105129,0.0006773606,0.0001489675,0.0002179886,0.002072767,0.0003467573,0.00001595913],"category_scores_gemma":[0.0001707432,0.0004192097,0.000296537,0.001027841,0.00008896914,0.0004560566,0.001674501,0.0008555966,0.000007904497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002459602,"about_ca_system_score_gemma":0.0004018772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007055447,"about_ca_topic_score_gemma":0.000005593783,"domain_scores_codex":[0.9976476,0.0002105681,0.000341136,0.001136222,0.0002301202,0.0004343583],"domain_scores_gemma":[0.9971844,0.0003233956,0.0006110389,0.001204567,0.0004911161,0.000185461],"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":[0.000007323588,0.00006936245,0.0003220074,0.00009742443,0.0001221752,0.00005564355,0.0003021828,0.974132,0.0000262709,0.01965677,0.00001024248,0.005198606],"study_design_scores_gemma":[0.0005556463,0.0002785639,0.0003982249,0.0001268092,0.00009956584,0.000004544764,0.0003320479,0.9966382,0.0001034944,0.00100036,0.00006308649,0.0003995011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02514192,0.00006406372,0.9732469,0.00001363243,0.0006067643,0.0004242836,0.000006383889,0.0001857711,0.000310277],"genre_scores_gemma":[0.9626042,0.0000454416,0.03610846,0.00002438545,0.0000607623,0.00000253554,0.00005185733,0.00002855935,0.00107376],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9374623,"threshold_uncertainty_score":0.999826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0524186279386688,"score_gpt":0.2089538804048337,"score_spread":0.1565352524661649,"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."}}