{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005469957,0.0001729292,0.0001476504,0.0001107782,0.0009690858,0.0005005496,0.0009796222,0.00006254482,0.00001048671],"category_scores_gemma":[0.0003110458,0.0001510371,0.00009523543,0.00008579067,0.00005582266,0.0004828775,0.0002220032,0.0002266947,0.0000845626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001315327,"about_ca_system_score_gemma":0.00007333457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005583973,"about_ca_topic_score_gemma":0.000001513189,"domain_scores_codex":[0.9985195,0.00008049042,0.0002293225,0.0004820458,0.0003747108,0.0003138939],"domain_scores_gemma":[0.998246,0.00004522785,0.000243652,0.001233906,0.0001292595,0.0001019674],"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":[0.00003427613,0.0003224541,0.0001893313,0.0000184469,0.00005141721,0.000003169311,0.0003116681,0.7554111,0.001729594,0.158367,0.0001791154,0.08338247],"study_design_scores_gemma":[0.000947081,0.0001865661,0.002667042,0.00001211417,0.00001070951,9.563381e-7,0.00003365351,0.9947104,0.0001384928,0.00009870841,0.00101491,0.0001793465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004794846,0.000003773309,0.9793389,0.0007368524,0.0002895971,0.0004961696,2.107193e-7,0.0003599287,0.01829507],"genre_scores_gemma":[0.6938025,3.278089e-7,0.3030628,0.0002696084,0.0000327467,0.0001008987,0.000008373823,0.000008812286,0.002713921],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6933231,"threshold_uncertainty_score":0.7453523,"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."}}