{"id":"W3153326893","doi":"","title":"Approximate Multi-Agent Fitted Q Iteration.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computation; Reinforcement learning; Mathematical optimization; Computer science; Function (biology); Property (philosophy); Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002392458,0.0008471334,0.001167111,0.0004508276,0.0004507122,0.000924882,0.002087934,0.001633127,0.003252202],"category_scores_gemma":[0.008767345,0.0005195522,0.0006724817,0.0004392831,0.00133316,0.001289198,0.001364807,0.001679993,0.0009312921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001308396,"about_ca_system_score_gemma":0.002683048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005103405,"about_ca_topic_score_gemma":0.004273933,"domain_scores_codex":[0.9988674,0.0004727045,0.00005074565,0.0001743912,0.0002975913,0.0001372208],"domain_scores_gemma":[0.9970222,0.001636776,0.0003154473,0.0003321173,0.0004987411,0.0001947901],"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":[0.0001103531,0.00005638925,0.0006732828,0.0000663864,0.00003129663,0.00005524745,0.00005626371,0.9440615,0.0009224648,0.02390088,0.001117002,0.02894907],"study_design_scores_gemma":[0.000007251181,0.00001691284,0.00002355404,0.000003282219,0.000001925053,0.000007720263,0.000002844781,0.995952,0.0001718176,0.003540424,0.0002703,0.000002085892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003750531,0.00008651509,0.9946485,0.0000915059,0.00002939709,0.00005196812,0.00001831123,0.0001986848,0.001124699],"genre_scores_gemma":[0.5351829,0.0001528178,0.4598502,0.0002784647,0.00005766383,0.0004127831,0.0001412673,0.0001284016,0.003795463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005103405,"threshold_uncertainty_score":0.0126527,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09705536036995745,"score_gpt":0.2000325766055295,"score_spread":0.1029772162355721,"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."}}