{"id":"W4378701136","doi":"10.1016/j.sysconle.2023.105563","title":"Approximated multi-agent fitted Q iteration","year":2023,"lang":"en","type":"article","venue":"Systems & Control Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"Computation; Reinforcement learning; Mathematical optimization; Computer science; Mathematics; Function (biology); Property (philosophy); Applied mathematics; Algorithm; Artificial intelligence","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000551164,0.0001911039,0.0002556243,0.0002380438,0.0001303191,0.000473637,0.0006189983,0.00006872255,0.000007910291],"category_scores_gemma":[0.00005085305,0.0001784589,0.00008091707,0.0006040134,0.00002079578,0.00039587,0.00009099865,0.0001569547,0.001437137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009919868,"about_ca_system_score_gemma":0.00002082639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004860388,"about_ca_topic_score_gemma":7.762582e-7,"domain_scores_codex":[0.9980423,0.0002068022,0.0004287494,0.0004045218,0.0004609917,0.0004566273],"domain_scores_gemma":[0.9988971,0.0001091733,0.0001991895,0.0006289081,0.00007497741,0.00009059175],"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":[0.000005067955,0.000008776001,0.002237941,0.00005870227,0.00006463579,0.00004020762,0.0004750649,0.9414461,0.04850687,0.001805866,0.005169001,0.0001818011],"study_design_scores_gemma":[0.001326146,0.000030596,0.003457156,0.00004897738,0.000007439311,0.0000067785,0.00002548348,0.9902568,0.00007532478,0.000001901719,0.004565798,0.0001975674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03008777,0.00002918222,0.963424,0.002445201,0.001855021,0.0008218975,0.000002241566,0.001173907,0.0001607801],"genre_scores_gemma":[0.9950206,0.000001888989,0.001927992,0.001573621,0.0001235491,0.0001132113,0.00002803328,0.00002222413,0.001188927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9649328,"threshold_uncertainty_score":0.9993404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02177352513042629,"score_gpt":0.2416513473809132,"score_spread":0.2198778222504869,"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."}}