{"id":"W7124267618","doi":"10.65109/odcq7385","title":"Centralized Model and Exploration Policy for Multi-Agent RL","year":2022,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Sample (material); Key (lock); Polynomial; Sample complexity; Robot; Swarm behaviour","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":[0.0005541653,0.0002619012,0.0002504202,0.0002376031,0.001062044,0.0004393682,0.0007026567,0.0000550233,0.0001146097],"category_scores_gemma":[0.0001241687,0.0002885122,0.0001159095,0.0004619092,0.0000627519,0.0008850948,0.001257909,0.0002293063,0.00001340397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00032033,"about_ca_system_score_gemma":0.0004191022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007028197,"about_ca_topic_score_gemma":0.000004199866,"domain_scores_codex":[0.9975045,0.0001462092,0.0005353432,0.0006277533,0.0005430782,0.0006430954],"domain_scores_gemma":[0.9987991,0.00007342192,0.000245288,0.0005596981,0.0001154396,0.0002069936],"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":[0.00002836665,0.00007602939,0.00003521467,0.00003620883,0.00002584714,0.00000107061,0.004744689,0.8765028,0.0002000749,0.1116192,0.001047267,0.005683227],"study_design_scores_gemma":[0.002103404,0.0003524584,0.00003046913,0.000006937446,0.00002216327,0.00000465685,0.0003689411,0.9884215,0.0001416736,0.0009137436,0.007309912,0.0003241183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006247833,0.0001063704,0.9919884,0.004756862,0.000632472,0.001222423,0.00001232284,0.0001194013,0.0005369191],"genre_scores_gemma":[0.5623993,0.0002663171,0.402007,0.002070615,0.0001280499,0.0003105669,0.00003045986,0.00003926628,0.0327485],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5899815,"threshold_uncertainty_score":0.9999567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1278619622167838,"score_gpt":0.334491336757149,"score_spread":0.2066293745403652,"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."}}