{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007985642,0.0001543755,0.0002545797,0.0003120653,0.00007923,0.0006377983,0.000489466,0.00005922564,0.000001677906],"category_scores_gemma":[0.000401056,0.0001260705,0.0001735743,0.0001049107,0.00004621338,0.0002169462,0.00008948857,0.0002700638,0.000003805091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001478933,"about_ca_system_score_gemma":0.0002002624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001953585,"about_ca_topic_score_gemma":0.000001708789,"domain_scores_codex":[0.9985153,0.00007672072,0.000483387,0.0002300143,0.0004554541,0.0002390908],"domain_scores_gemma":[0.9985214,0.0004257478,0.0002534511,0.00008685583,0.0005930756,0.0001193972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004143796,0.0004384282,0.0007399664,0.0001119944,0.002126326,0.0005250812,0.001524836,0.4596397,0.007646901,0.02463928,0.001899544,0.5002935],"study_design_scores_gemma":[0.001888341,0.0001757585,0.0000620847,0.0001642206,0.00003058151,0.0002683981,0.00005891148,0.9621257,0.00002292754,0.00002507684,0.03505901,0.0001190599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009577744,0.008248172,0.977106,0.002804038,0.001945219,0.0002132201,0.00003010957,0.00005753961,0.00001795326],"genre_scores_gemma":[0.9606973,0.0001011694,0.03723099,0.000150267,0.001383835,0.00001375548,0.000004501938,0.00001937209,0.0003988349],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9511195,"threshold_uncertainty_score":0.6150303,"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."}}