{"id":"W3013464227","doi":"10.1109/ieeeconf44664.2019.9049021","title":"Decentralized Q-Learning with Constant Aspirations in Stochastic Games","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Constant (computer programming); Mathematical optimization; State (computer science); Control (management); Information structure; Fictitious play; Complete information; Function (biology); Obstacle; Nash equilibrium; Artificial intelligence; Mathematical economics; Mathematics; Algorithm; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000154886,0.0001006216,0.0001318623,0.0001134404,0.00004431952,0.0001433855,0.0003305821,0.00003080601,0.0001915719],"category_scores_gemma":[0.00005316716,0.0000790432,0.00001944448,0.0003687801,0.00002922641,0.0003402178,0.0000877366,0.0001851052,0.0002613165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004459599,"about_ca_system_score_gemma":0.00009634489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001933238,"about_ca_topic_score_gemma":0.00001686932,"domain_scores_codex":[0.9990165,0.00004924922,0.0001851239,0.0002328432,0.0002448882,0.000271415],"domain_scores_gemma":[0.9994047,0.0001329762,0.00007111941,0.0002906776,0.00004666291,0.00005391167],"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":[0.000004332576,0.000008654537,0.01077673,0.000003301123,0.000005822182,0.000003603366,0.0002642008,0.9015005,0.0001053077,0.08692231,0.00001716071,0.000388081],"study_design_scores_gemma":[0.0008248688,0.0001986452,0.002693383,0.00004777273,0.000002595911,0.000008474337,0.0001103808,0.9948853,0.00006997607,0.0001063612,0.0008929417,0.0001592661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02171635,0.00001581729,0.960365,0.0002279614,0.00008758692,0.0002347372,5.588271e-8,0.0001541479,0.01719837],"genre_scores_gemma":[0.9650533,0.000002922896,0.03230764,0.0001713313,0.000004235932,0.000006980653,0.000001477208,0.000007039018,0.002445063],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.943337,"threshold_uncertainty_score":0.3358782,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01277884051352069,"score_gpt":0.2252136990534358,"score_spread":0.2124348585399151,"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."}}