{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003198045,0.00119217,0.001407293,0.0007542198,0.0006684507,0.001037887,0.00314793,0.001731498,0.002807065],"category_scores_gemma":[0.01158019,0.0006666098,0.001001323,0.0005659568,0.001786612,0.00247259,0.002348924,0.003147786,0.0007380357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00125121,"about_ca_system_score_gemma":0.002437901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00143199,"about_ca_topic_score_gemma":0.001531751,"domain_scores_codex":[0.9985473,0.0004987306,0.00007488478,0.000415056,0.0003201793,0.0001437998],"domain_scores_gemma":[0.9948277,0.003528561,0.000400961,0.0004289799,0.0005332772,0.0002804955],"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":[0.0002655404,0.0002857537,0.00148466,0.0001263898,0.0001255283,0.0001492543,0.0002774184,0.6849149,0.002469828,0.1781745,0.002722802,0.1290035],"study_design_scores_gemma":[0.00004270717,0.00005480787,0.0000497375,0.000007787908,0.000007883407,0.00003037999,0.000008162467,0.9645538,0.000518312,0.03434579,0.0003728771,0.00000768607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01540862,0.00005336558,0.9823564,0.0001374309,0.0000204869,0.0001310921,0.00002670579,0.000171593,0.001694424],"genre_scores_gemma":[0.4703122,0.0001737477,0.5223868,0.0002769069,0.00006204656,0.0008629182,0.0002631716,0.0001602684,0.005501858],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003198045,"threshold_uncertainty_score":0.01691306,"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."}}