{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002108314,0.0003420487,0.0003201268,0.00022699,0.00019752,0.0005537365,0.001851565,0.0002790384,0.00007388366],"category_scores_gemma":[0.00006220125,0.0004164275,0.0002240507,0.0005727747,0.00006522302,0.0005252956,0.003092967,0.0006806307,0.0001274597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002588747,"about_ca_system_score_gemma":0.0002277037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004324085,"about_ca_topic_score_gemma":0.000008269858,"domain_scores_codex":[0.9978666,0.0001781096,0.0002720168,0.00114317,0.0001496874,0.0003903929],"domain_scores_gemma":[0.9975443,0.00006448375,0.0003104092,0.001651914,0.0002653556,0.0001635079],"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":[0.000003180292,0.00005218051,0.0009994535,0.00007209658,0.00007846316,0.0003298648,0.0004212445,0.9813967,0.00004545814,0.01632284,0.0001590942,0.0001194645],"study_design_scores_gemma":[0.0004161106,0.00002259642,0.0007388131,0.00009661823,0.00003847494,0.000004552459,0.00006546156,0.9972306,0.0001805732,0.0003011295,0.00047751,0.0004275531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02728065,0.00004674159,0.9698055,0.00008695504,0.0009790083,0.0002968709,0.000003106992,0.0003868955,0.001114269],"genre_scores_gemma":[0.9540498,0.0001146316,0.038466,0.0001914277,0.00005450157,0.000001501358,0.0000777806,0.00002231134,0.007021995],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9313395,"threshold_uncertainty_score":0.9998288,"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."}}