{"id":"W4399968983","doi":"10.1007/s44196-024-00560-2","title":"Multi-agent Gradient-Based Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"International Journal of Computational Intelligence Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Wenzhou University; McGill University","keywords":"Reinforcement learning; Temporal difference learning; Generalization; Convergence (economics); Computer science; Stability (learning theory); Algorithm; Set (abstract data type); Rate of convergence; Mathematical optimization; Mathematics; Artificial intelligence; Machine learning; Key (lock)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009612139,0.0002453869,0.0003100186,0.0007572325,0.0001151072,0.0008787618,0.00145491,0.00007363263,0.000006376977],"category_scores_gemma":[0.0004312711,0.0002230683,0.0003508844,0.0004061955,0.00008593927,0.0006971409,0.0001148522,0.0003346827,0.00003031643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008873103,"about_ca_system_score_gemma":0.0008207517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004018038,"about_ca_topic_score_gemma":0.000001217552,"domain_scores_codex":[0.9968323,0.0001368734,0.001144922,0.0003397554,0.001213994,0.0003321646],"domain_scores_gemma":[0.9957617,0.001039023,0.0005009926,0.0001472655,0.002373108,0.0001779341],"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":[0.00001775156,0.00007849432,0.00002116748,0.00003096121,0.0003068938,0.00009456737,0.0002225346,0.770615,0.00004583078,0.05055394,0.0001311757,0.1778816],"study_design_scores_gemma":[0.0004249856,0.000289388,0.00006012032,0.0004101699,0.00002110774,0.0002630238,0.0001105023,0.9813492,0.0001151568,0.003190732,0.01356221,0.0002034255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000209692,0.001158783,0.9918543,0.001440756,0.004776507,0.0003763431,0.00004872985,0.0001176356,0.00001724602],"genre_scores_gemma":[0.8587925,0.0000214891,0.1400208,0.0001214995,0.0007442385,0.00004377202,0.00008283251,0.00002102263,0.0001518018],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8585829,"threshold_uncertainty_score":0.9096462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02751854041541726,"score_gpt":0.3322516421591333,"score_spread":0.304733101743716,"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."}}