{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001145867,0.0003663723,0.0003002185,0.0003059977,0.002033071,0.0005607147,0.001341735,0.00005971931,0.002029021],"category_scores_gemma":[0.0001048981,0.0003638145,0.0001079174,0.001405018,0.0001053742,0.0006729992,0.001898999,0.001275902,0.0002608602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005473968,"about_ca_system_score_gemma":0.0003199742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007417752,"about_ca_topic_score_gemma":0.000004280241,"domain_scores_codex":[0.9955371,0.0006040861,0.0005522654,0.000849937,0.001700022,0.0007566131],"domain_scores_gemma":[0.998139,0.0001929333,0.0004913184,0.0007444751,0.000229692,0.0002025836],"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":[0.00003391551,0.0001075653,0.00463886,0.00002457322,0.00006628704,0.00003660685,0.002468008,0.969704,0.0003052891,0.007331854,0.002013743,0.0132693],"study_design_scores_gemma":[0.001028682,0.002033889,0.001185169,0.00002070615,0.00003284357,0.00006421587,0.001006654,0.9424774,0.0007091583,0.00001230855,0.05092186,0.0005070828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01153499,0.00009464612,0.9635098,0.001244202,0.001028892,0.000613574,7.85354e-7,0.0003469099,0.02162622],"genre_scores_gemma":[0.9445629,0.00002155715,0.01279534,0.0004480477,0.00007587992,0.00007088198,0.00001729911,0.00004280156,0.04196535],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9507145,"threshold_uncertainty_score":0.9998814,"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."}}