{"id":"W4390733893","doi":"10.1002/rnc.7189","title":"Efficient off‐policy Q‐learning for multi‐agent systems by solving dual games","year":2024,"lang":"en","type":"article","venue":"International Journal of Robust and Nonlinear Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Dual (grammatical number); Bounded function; Synchronization (alternating current); Nash equilibrium; Tracking (education); Mathematical optimization; Zero-sum game; Tracking error; Zero (linguistics); Multi-agent system; Potential game; Game theory; Control (management); Artificial neural network; Control theory (sociology); Artificial intelligence; Mathematics; Mathematical economics; Channel (broadcasting)","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":[0.001832891,0.0009291578,0.00141584,0.000476893,0.0005752679,0.001220961,0.001093778,0.001118417,0.001513742],"category_scores_gemma":[0.003150873,0.0005175109,0.0004938088,0.0003859104,0.00135346,0.0009606265,0.001516516,0.00127526,0.0001710085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00122033,"about_ca_system_score_gemma":0.001902119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005834642,"about_ca_topic_score_gemma":0.00276055,"domain_scores_codex":[0.99925,0.0002766642,0.00003318906,0.0001471998,0.0001572289,0.0001356417],"domain_scores_gemma":[0.9987646,0.0007197409,0.000153197,0.00005305496,0.0002281366,0.00008127242],"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":[0.00005213392,0.00004150129,0.0003733607,0.00004580179,0.00002219312,0.00004659339,0.00004618911,0.9736958,0.0007402786,0.0140683,0.0003248336,0.01054299],"study_design_scores_gemma":[0.000006377641,0.00001166998,0.00001551817,0.000001595516,0.000001435408,0.000002237367,0.000002680785,0.9981831,0.00006670005,0.001634873,0.00007255047,0.000001233366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01645013,0.0001581011,0.9806908,0.0002006532,0.00002908264,0.00004635795,0.00001179543,0.00009277689,0.002320267],"genre_scores_gemma":[0.9451432,0.0001355006,0.05209716,0.0001336304,0.00002896898,0.000166486,0.00003139602,0.00002369282,0.002239964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005834642,"threshold_uncertainty_score":0.01160133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01596171939074153,"score_gpt":0.2841705815956896,"score_spread":0.2682088622049481,"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."}}