{"id":"W3118394271","doi":"10.1609/aaai.v35i11.17166","title":"Solving Common-Payoff Games with Approximate Policy Iteration","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Stochastic game; Scalability; Artificial intelligence; Common knowledge (logic); Scale (ratio); Mathematical optimization; Mathematical economics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003355165,0.0002292444,0.0002610578,0.0001382842,0.0002612367,0.0007141838,0.001485701,0.0000733031,0.0000378282],"category_scores_gemma":[0.0004276735,0.0001673928,0.00008342806,0.001021526,0.0002053298,0.00065761,0.0004959741,0.0003285132,0.00004412198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006774392,"about_ca_system_score_gemma":0.0002760211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002914542,"about_ca_topic_score_gemma":0.000008218251,"domain_scores_codex":[0.9980127,0.00002512185,0.0004969419,0.0004675861,0.0006163224,0.0003813361],"domain_scores_gemma":[0.9980826,0.00009105094,0.0004246875,0.0004299217,0.0008891513,0.00008257645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002392836,0.00006564477,0.0005028172,0.000056044,0.0000199446,0.000001823003,0.001746334,0.01142812,0.02177807,0.9437625,0.00007548477,0.02053924],"study_design_scores_gemma":[0.00003167958,0.0001641047,0.0001740217,0.0003138223,0.00001018435,0.00001853793,0.0003815904,0.4685182,0.4953234,0.03469945,0.0001416295,0.0002234541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05475348,0.00002934383,0.8946324,0.01019013,0.0003856004,0.0004826482,0.000002322977,0.0002312643,0.03929281],"genre_scores_gemma":[0.9832203,0.00002305739,0.01536687,0.0004037641,0.00007933892,0.00001656638,0.00000115814,0.00001498072,0.0008738977],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9284669,"threshold_uncertainty_score":0.6886891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04921359465533086,"score_gpt":0.2888286847180552,"score_spread":0.2396150900627244,"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."}}