{"id":"W7125902845","doi":"10.1109/smc58881.2025.11342876","title":"Reinforcement Learning Task Assignment for Multi-Pursuer Multi-Evader Reach-Avoid Games","year":2025,"lang":"","type":"article","venue":"","topic":"Guidance and Control Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Reinforcement learning; Task (project management); Decomposition; Homogeneous; Assignment problem; Optimization problem; Task analysis","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":[0.001177517,0.0009412226,0.001226961,0.000461851,0.0004459847,0.0006339224,0.001396203,0.001033874,0.002139493],"category_scores_gemma":[0.004038657,0.0003696966,0.0004837029,0.0002936627,0.0009709075,0.0007868307,0.001329695,0.001409356,0.0002847065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009376929,"about_ca_system_score_gemma":0.00127783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004735665,"about_ca_topic_score_gemma":0.003388168,"domain_scores_codex":[0.9994247,0.0002170578,0.00002161457,0.0001040371,0.0001112313,0.0001213861],"domain_scores_gemma":[0.9983128,0.001040697,0.0002110326,0.00007357502,0.0001483134,0.0002136701],"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":[0.00006258736,0.000071164,0.0003881668,0.00003117211,0.00001697187,0.00006127539,0.00004116158,0.979991,0.0008634523,0.005941837,0.0004935286,0.01203768],"study_design_scores_gemma":[0.00000878133,0.00001697453,0.00003962178,0.000001328271,0.000001803236,0.000005007609,0.000003804091,0.9979886,0.00007945911,0.001766326,0.00008637134,0.000001923411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07538689,0.0002028763,0.9186915,0.0003191544,0.00004524811,0.00009736128,0.0000397514,0.0003554772,0.004861631],"genre_scores_gemma":[0.9492101,0.00007436052,0.04752523,0.0001024106,0.00002545704,0.0001425379,0.00005011362,0.00003979348,0.002830043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004735665,"threshold_uncertainty_score":0.009416223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02578360523108296,"score_gpt":0.2749910369501467,"score_spread":0.2492074317190637,"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."}}