{"id":"W4386735338","doi":"10.1007/978-3-031-43520-1_13","title":"A Relaxed Variant of Distributed Q-Learning Algorithm for Cooperative Matrix Games","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Algorithm; Computer science; Convergence (economics); Population-based incremental learning; Matrix (chemical analysis); Distributed algorithm; Q-learning; Weighted Majority Algorithm; Function (biology); Distributed learning; Artificial intelligence; Wake-sleep algorithm; Machine learning; Unsupervised learning; Reinforcement learning; Distributed computing; Genetic algorithm","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":[0.003003632,0.001126189,0.001862942,0.0005550981,0.0006240889,0.001209807,0.004513896,0.001886575,0.008530164],"category_scores_gemma":[0.006726442,0.0005708588,0.0008873157,0.0009329537,0.001607913,0.001695229,0.003147975,0.002703686,0.001740569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004879,"about_ca_system_score_gemma":0.002305001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003778052,"about_ca_topic_score_gemma":0.002875574,"domain_scores_codex":[0.9981691,0.0007366303,0.00007841743,0.000347598,0.00046667,0.0002016253],"domain_scores_gemma":[0.9970787,0.001606016,0.0001226207,0.000397566,0.0006174783,0.0001776112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002990675,0.0001717633,0.000302792,0.000159143,0.00007865215,0.00008501633,0.0001176137,0.7887737,0.002538309,0.08874973,0.006064347,0.11266],"study_design_scores_gemma":[0.00003252505,0.00003727206,0.00003153548,0.000005571968,0.000004841088,0.00001312112,0.000005144257,0.9869612,0.0001800552,0.01212495,0.0005983402,0.000005543373],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00277856,0.00006658598,0.9944816,0.00008190873,0.00006640696,0.00005724294,0.00002654505,0.0001176182,0.002323465],"genre_scores_gemma":[0.3357725,0.0002155336,0.6492017,0.0003936279,0.0002296103,0.0006838105,0.0003226305,0.0002509998,0.01292959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008530164,"threshold_uncertainty_score":0.02853626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01637866089937328,"score_gpt":0.245987240694854,"score_spread":0.2296085797954807,"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."}}