{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001957893,0.000850093,0.001278865,0.0004242547,0.00048685,0.000759735,0.001654936,0.001404759,0.002004767],"category_scores_gemma":[0.005247273,0.000422405,0.0005738657,0.0004660689,0.001497105,0.001251084,0.001707531,0.001555974,0.0002354398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001069498,"about_ca_system_score_gemma":0.001505532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006424525,"about_ca_topic_score_gemma":0.004256695,"domain_scores_codex":[0.9994516,0.0001935998,0.00002147883,0.000122654,0.0001034901,0.000107186],"domain_scores_gemma":[0.9976452,0.00151087,0.0002741333,0.0001735322,0.0002453646,0.000150913],"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":[0.00002889046,0.00002354213,0.0002422496,0.0000213231,0.00001218716,0.00002209393,0.00002008577,0.9835866,0.0003208,0.006469594,0.000331331,0.008921338],"study_design_scores_gemma":[0.000007918264,0.00001807546,0.00002862732,0.000001930801,0.000001528407,0.000003551626,0.000002173819,0.9963924,0.0000673782,0.003333993,0.0001405706,0.000001765712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0241654,0.0002038262,0.9731933,0.0002939885,0.00004311127,0.00004514844,0.00003476214,0.0002659184,0.001754559],"genre_scores_gemma":[0.9086525,0.0001552647,0.0887773,0.000201647,0.00004154293,0.0001390162,0.00008582149,0.00004961097,0.00189731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006424525,"threshold_uncertainty_score":0.01277423,"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."}}