{"id":"W2783810978","doi":"10.1109/iris.2017.8250107","title":"Multi-agent reinforcement learning approach based on reduced value function approximations","year":2017,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Bellman equation; Convergence (economics); Computer science; Mathematical optimization; Graph; Function approximation; Artificial neural network; Function (biology); Markov decision process; Artificial intelligence; Mathematics; Theoretical computer science; Markov process","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":[0.0008235368,0.0006378317,0.001268667,0.0004285123,0.0003107388,0.0007212919,0.001499456,0.0008315143,0.002103215],"category_scores_gemma":[0.001995729,0.0003492068,0.0005373831,0.0003077563,0.0007200076,0.0008478928,0.0007730759,0.001312878,0.0003863907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008272929,"about_ca_system_score_gemma":0.0009423521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004318486,"about_ca_topic_score_gemma":0.002499313,"domain_scores_codex":[0.9995452,0.0001892672,0.00001520398,0.00006466621,0.0001409825,0.00004469636],"domain_scores_gemma":[0.9992909,0.0004183422,0.00006995454,0.00005069223,0.000130446,0.00003963022],"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":[0.00002732002,0.00002687475,0.0001521188,0.00003810358,0.00002896018,0.00005060527,0.00004003653,0.9582337,0.0007701286,0.02476405,0.0004194801,0.01544858],"study_design_scores_gemma":[0.000003023431,0.000006018288,0.00000906439,0.000001168557,0.000001392746,0.000002915768,0.000001143867,0.9972985,0.00007430888,0.002458502,0.0001428093,0.000001264638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00683229,0.0001391089,0.9903831,0.0001266,0.00003144861,0.00002342131,0.00001192833,0.0001674811,0.002284565],"genre_scores_gemma":[0.7905774,0.0002677822,0.2037526,0.0001290015,0.00005675225,0.0002235416,0.00007083188,0.00009150798,0.004830619],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004318486,"threshold_uncertainty_score":0.008586705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03350929300342959,"score_gpt":0.2669293575365366,"score_spread":0.233420064533107,"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."}}