{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002443211,0.0007065682,0.000780563,0.0003353389,0.0004158122,0.0005841029,0.001382223,0.0008075864,0.001147171],"category_scores_gemma":[0.006488399,0.0004548474,0.0003449004,0.0002521557,0.001183491,0.001237512,0.001737593,0.001640367,0.0001926473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008925709,"about_ca_system_score_gemma":0.001396463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002227353,"about_ca_topic_score_gemma":0.003152945,"domain_scores_codex":[0.9992035,0.0003516119,0.00003999484,0.000131902,0.0001731768,0.00009979757],"domain_scores_gemma":[0.9972267,0.00175332,0.0003129922,0.0002806056,0.0002306526,0.0001957385],"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":[0.00009688806,0.00005284604,0.001035339,0.00004738616,0.00003531308,0.00005362069,0.00008767552,0.9505045,0.001787039,0.0140143,0.0006010257,0.03168403],"study_design_scores_gemma":[0.00000498784,0.0000157138,0.00003492574,0.000002673087,0.000002179011,0.00000531167,0.000003314379,0.9960054,0.0002644778,0.003516463,0.0001426204,0.00000199507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02804512,0.000162008,0.9700361,0.0001687485,0.0000189474,0.00003605067,0.00001628543,0.0003856864,0.001131002],"genre_scores_gemma":[0.8828496,0.00007775189,0.115565,0.0001022361,0.00002117021,0.0001347803,0.00004429206,0.00006056802,0.001144703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002443211,"threshold_uncertainty_score":0.01292109,"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."}}