{"id":"W4403577538","doi":"10.48550/arxiv.2410.12062","title":"MFC-EQ: Mean-Field Control with Envelope Q-Learning for Moving Decentralized Agents in Formation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Envelope (radar); Mean field theory; Field (mathematics); Control (management); Decentralised system; Physics; Computer science; Mathematics; Artificial intelligence; Telecommunications; Pure mathematics; Condensed matter physics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004482436,0.0003347008,0.0003750676,0.0004408511,0.0001484101,0.0003189225,0.001171222,0.0002609829,0.00001842424],"category_scores_gemma":[0.000124503,0.0003521393,0.0001533255,0.0005586609,0.00003333009,0.0005464137,0.001004955,0.0009423526,0.00005151405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004232533,"about_ca_system_score_gemma":0.0002112243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009251073,"about_ca_topic_score_gemma":0.00006558144,"domain_scores_codex":[0.9980502,0.0001399273,0.0003316564,0.0007962941,0.0001658402,0.0005160595],"domain_scores_gemma":[0.998518,0.0003039615,0.0003268103,0.0005837058,0.0001465539,0.0001209395],"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":[0.00008995103,0.00001597837,0.002659053,0.0002362732,0.00008438368,0.0001143649,0.0008732788,0.9701405,0.0000125517,0.02509131,0.0001116622,0.0005707389],"study_design_scores_gemma":[0.001572499,0.0001430865,0.0003598511,0.0004222236,0.00007702156,0.000003651529,0.0001238803,0.9928536,0.0001303252,0.002942072,0.0009667865,0.0004050048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04828192,0.00003686171,0.9484831,0.0001682436,0.0004020616,0.0008044976,0.000001988463,0.00027393,0.001547397],"genre_scores_gemma":[0.9926026,0.0001102283,0.005764163,0.0001677434,0.00003234901,0.000006516795,0.00002187534,0.00002864824,0.001265842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9443207,"threshold_uncertainty_score":0.9998931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06673068477514002,"score_gpt":0.2092939527591059,"score_spread":0.1425632679839659,"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."}}