{"id":"W6948085940","doi":"10.48448/43gf-5e17","title":"A Very Short Survey and Critique of Multiagent Deep Reinforcement Learning","year":2020,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Wood and Agarwood Research","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Control (management); Feature (linguistics); Action (physics); Deep learning","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":[0.0006418734,0.0002203183,0.0003217447,0.0002075328,0.0001200778,0.00007392557,0.0005197074,0.0001691962,0.002102193],"category_scores_gemma":[0.0006420043,0.0001954278,0.0000432026,0.0003455864,0.0007267673,0.00006269103,0.0004320511,0.0005055761,0.00001911732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006074796,"about_ca_system_score_gemma":0.0003782345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007925952,"about_ca_topic_score_gemma":0.0004002131,"domain_scores_codex":[0.9979522,0.00003937465,0.0002849187,0.0005291869,0.0007932425,0.0004010758],"domain_scores_gemma":[0.999115,0.0001474947,0.0001046204,0.000288227,0.0001054434,0.0002391762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003290399,0.001077427,0.09579405,0.01056398,0.0009680143,0.0005445502,0.004076197,0.005434954,0.5102044,0.002126213,0.2363356,0.1325455],"study_design_scores_gemma":[0.00333582,0.001089322,0.003730384,0.003524528,0.0001683609,0.00005245394,0.004205466,0.2917084,0.2227434,0.0001490347,0.4653429,0.003949873],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.008104197,0.002381617,0.005010553,0.0004255775,0.0002766544,0.000494713,0.00007261371,0.0003477348,0.9828863],"genre_scores_gemma":[0.8821877,0.0006540411,0.0007923955,0.00008676999,0.0001869504,0.00001137417,0.0001374985,0.0001434324,0.1157999],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8740835,"threshold_uncertainty_score":0.99881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03723244887752088,"score_gpt":0.3228721900761363,"score_spread":0.2856397411986154,"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."}}