{"id":"W7124291660","doi":"10.65109/mrqs8697","title":"Multiagent Q-learning with Sub-Team Coordination","year":2022,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Exploit; Factorization; Class (philosophy); Monotonic function; Function (biology); Ranging","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":[0.002613289,0.0009156265,0.001229354,0.000343121,0.0004976945,0.0008075255,0.001969558,0.001033151,0.002643918],"category_scores_gemma":[0.005428004,0.0003824488,0.0004771777,0.0004261514,0.0011956,0.001261842,0.001841129,0.001555679,0.0004939964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007007341,"about_ca_system_score_gemma":0.001565668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002360354,"about_ca_topic_score_gemma":0.001889039,"domain_scores_codex":[0.9988316,0.0005035324,0.00005086772,0.000265759,0.0002245541,0.0001237436],"domain_scores_gemma":[0.9978738,0.00113451,0.0002643886,0.0002304385,0.0002904214,0.0002065059],"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":[0.0001034178,0.0001271832,0.0008602294,0.00009520254,0.00006084044,0.00007802046,0.0001151397,0.8857182,0.001655524,0.03551375,0.001896688,0.0737758],"study_design_scores_gemma":[0.00001559061,0.00003507639,0.00004027085,0.000003276616,0.000003427612,0.000007581882,0.000005335603,0.9904992,0.0001950657,0.008847818,0.0003444358,0.000002932916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006772934,0.00009893136,0.991593,0.0001244956,0.00003039569,0.00004056021,0.0000119246,0.0001327558,0.001194982],"genre_scores_gemma":[0.7793539,0.0001447112,0.2174259,0.000260326,0.00008206604,0.0002638722,0.0000721307,0.00005485155,0.00234223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002643918,"threshold_uncertainty_score":0.01382059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01297200780350696,"score_gpt":0.2224307060249066,"score_spread":0.2094586982213997,"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."}}