{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001759826,0.001074183,0.001771412,0.000399735,0.0005443476,0.001295206,0.002044027,0.001349892,0.002439772],"category_scores_gemma":[0.006397883,0.0007237901,0.0008618975,0.0005987547,0.001485355,0.001867628,0.001755845,0.003190676,0.0005206915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001942488,"about_ca_system_score_gemma":0.002966158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005033649,"about_ca_topic_score_gemma":0.005224934,"domain_scores_codex":[0.9989843,0.0003289134,0.00004463283,0.0002838151,0.000230146,0.0001280645],"domain_scores_gemma":[0.9969505,0.001726932,0.0003491777,0.0004659129,0.0003198548,0.000187692],"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":[0.00002884582,0.00002504737,0.0001807502,0.00002541111,0.00001067605,0.00001833588,0.00001968531,0.9860826,0.0002937199,0.006344038,0.0004070607,0.006563778],"study_design_scores_gemma":[0.000008278294,0.000009677588,0.00002182118,0.000002929794,0.000001910428,0.000003945922,0.000002805993,0.9955214,0.0001254443,0.004205293,0.00009417993,0.000002253988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00846954,0.000146627,0.9892024,0.0002506798,0.00002198899,0.00003726372,0.0000545754,0.0004885599,0.001328329],"genre_scores_gemma":[0.7949906,0.0001856883,0.2013102,0.000263862,0.00005902596,0.0003296071,0.0002258798,0.0001750949,0.002460044],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005033649,"threshold_uncertainty_score":0.01409376,"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."}}