{"id":"W4383108558","doi":"10.1109/icra48891.2023.10160919","title":"Multi-Target Pursuit by a Decentralized Heterogeneous UAV Swarm using Deep Multi-Agent Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Guidance and Control Systems","field":"Engineering","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"National Research Foundation Singapore","keywords":"Reinforcement learning; Computer science; Drone; Artificial intelligence; Pursuit-evasion; Swarm robotics; Swarm behaviour; Distributed computing; Robot; Evasion (ethics); Machine learning","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":[0.0002320736,0.000292372,0.0003346676,0.0001103538,0.0001449019,0.0001076148,0.0002298202,0.0001125475,0.0001764576],"category_scores_gemma":[0.00002955106,0.0002852256,0.0001510517,0.0002727033,0.00001538403,0.0001176283,0.00006500819,0.0001701092,0.0005225305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001928463,"about_ca_system_score_gemma":0.00001369834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002156771,"about_ca_topic_score_gemma":0.00005746545,"domain_scores_codex":[0.998107,0.00004565504,0.0004762173,0.000284694,0.0003176284,0.0007688378],"domain_scores_gemma":[0.9994344,0.00002878387,0.00005811915,0.0002532123,0.00004039716,0.0001850979],"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":[0.000007819158,0.00001686229,0.0008396567,0.00005084335,0.0001221953,0.00002922993,0.0003664292,0.9038029,0.09329281,0.00000269426,0.0006015798,0.000866996],"study_design_scores_gemma":[0.001709688,0.0000269295,0.0001021568,0.00003307233,0.00002324717,0.00001040257,0.0002302354,0.9580893,0.01668001,0.000001203912,0.0227614,0.0003323759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4110667,0.002875773,0.5811843,0.00003988025,0.001101097,0.0008743805,0.000006423025,0.002441893,0.0004095169],"genre_scores_gemma":[0.9936339,0.0002110079,0.003500682,0.00007946829,0.00006389844,0.00008959475,0.00005076648,0.00008572379,0.00228502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5825671,"threshold_uncertainty_score":0.99996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0250543128912482,"score_gpt":0.2508895084978031,"score_spread":0.2258351956065549,"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."}}