{"id":"W4406755395","doi":"10.1109/tii.2024.3523576","title":"A Deep Reinforcement Learning Approach Using Asymmetric Self-Play for Robust Multirobot Flocking","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Distributed Control Multi-Agent Systems","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"National Natural Science Foundation of China","keywords":"Flocking (texture); Reinforcement learning; Computer science; Artificial intelligence; Robustness (evolution); Materials science","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":[0.0008221717,0.0007583314,0.0008740707,0.0003088742,0.0003975978,0.0006513536,0.001433424,0.001001408,0.002206072],"category_scores_gemma":[0.001615685,0.0003990769,0.0004048779,0.0001784745,0.0009144254,0.0007658927,0.001437525,0.001289995,0.0003365663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008834709,"about_ca_system_score_gemma":0.001072713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00581684,"about_ca_topic_score_gemma":0.004435978,"domain_scores_codex":[0.9997298,0.00006060562,0.00001389801,0.00006474456,0.00006389982,0.00006697659],"domain_scores_gemma":[0.9995179,0.0002041178,0.00006840617,0.00004669573,0.00009658792,0.00006621004],"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":[0.00008604603,0.00007207711,0.0004898173,0.00003045836,0.00003390629,0.00006772897,0.00004401488,0.9411295,0.002465341,0.007702247,0.001115844,0.04676296],"study_design_scores_gemma":[0.000003877747,0.00001121636,0.00001707052,0.000001116262,0.000001512822,0.000002575199,0.000001144284,0.9988158,0.0001380041,0.0009260096,0.00008034952,0.000001379984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04738859,0.0003172097,0.9467647,0.0003566539,0.00008501705,0.00004245786,0.00003292992,0.0008342639,0.004178156],"genre_scores_gemma":[0.9489211,0.0000999557,0.04677996,0.0001672685,0.00003078598,0.00007411053,0.00006155026,0.00005484699,0.003810502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00581684,"threshold_uncertainty_score":0.01156598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06397134551297427,"score_gpt":0.2719946914471489,"score_spread":0.2080233459341747,"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."}}