{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008468567,0.0007882262,0.0009433292,0.0002998178,0.0004171852,0.0002980696,0.0004707513,0.0004407001,0.0003076557],"category_scores_gemma":[0.0002000409,0.0007694392,0.0005176092,0.0003230855,0.00006477197,0.000317211,0.0001618023,0.0006027779,0.000281928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006439874,"about_ca_system_score_gemma":0.0001402371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003326604,"about_ca_topic_score_gemma":0.0001010413,"domain_scores_codex":[0.9958163,0.000124232,0.00143805,0.0008533812,0.000450456,0.001317566],"domain_scores_gemma":[0.9983784,0.0002098435,0.0002291425,0.0007333736,0.0002163213,0.0002329009],"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":[0.0001535011,0.000284108,0.001525619,0.001650472,0.001618509,0.000008774065,0.001722599,0.9041323,0.04043349,0.005594461,0.01132688,0.0315493],"study_design_scores_gemma":[0.006895047,0.0001973195,0.0005257309,0.0007265072,0.0002634969,0.00000163306,0.002144939,0.8041712,0.004056278,0.00001590634,0.1802713,0.0007306605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005642583,0.006371767,0.9727574,0.000830897,0.002681589,0.002962413,0.00001094374,0.0004673661,0.01335337],"genre_scores_gemma":[0.8116034,0.0002654242,0.007275964,0.0003684009,0.0002908817,0.00110199,0.00003346633,0.00009846002,0.1789621],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9654815,"threshold_uncertainty_score":0.9994757,"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."}}