{"id":"W4327810476","doi":"10.48550/arxiv.2303.09032","title":"Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning","year":2023,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Monte Carlo tree search; Intuition; Tree (set theory); Artificial intelligence; Software deployment; Machine learning; Mathematical optimization; Mathematics; Cognitive science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001532111,0.0008273529,0.0007526638,0.000792005,0.0007745167,0.001259226,0.002093755,0.0006902859,0.00002602123],"category_scores_gemma":[0.001458614,0.0009200909,0.0004134456,0.0005457549,0.0001169086,0.0008170648,0.002340848,0.001535238,0.0001197017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001452201,"about_ca_system_score_gemma":0.0008488655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007925,"about_ca_topic_score_gemma":0.000315699,"domain_scores_codex":[0.9949285,0.0002948445,0.001387994,0.00133145,0.0009390386,0.001118136],"domain_scores_gemma":[0.9955222,0.0005473277,0.001140249,0.001590228,0.0008140961,0.0003859007],"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":[0.0000329144,0.00007040471,0.0002045762,0.0001788057,0.00017564,0.00003369529,0.0009508354,0.961639,0.000316073,0.03384902,0.001569878,0.0009791636],"study_design_scores_gemma":[0.0008384182,0.0003609086,0.0006724816,0.0002515844,0.00007035753,0.00001308774,0.0001382427,0.9918099,0.001283582,0.002023478,0.001631389,0.000906568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001876373,0.0002006243,0.9894354,0.002947467,0.0009758741,0.003470937,0.00003356456,0.00256403,0.0001844175],"genre_scores_gemma":[0.2265448,0.0004573395,0.751462,0.001321446,0.0003154245,0.007205947,0.001723953,0.0002047271,0.01076425],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2379734,"threshold_uncertainty_score":0.9997776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04615468709767459,"score_gpt":0.284435165013148,"score_spread":0.2382804779154734,"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."}}