{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00102433,0.0003721005,0.00047912,0.001005077,0.0008127392,0.0005649594,0.0008915566,0.0003996418,0.000004280772],"category_scores_gemma":[0.0001053347,0.000377183,0.0002696741,0.002024175,0.00003278564,0.001073127,0.0000142737,0.0007911449,0.00001832097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000658713,"about_ca_system_score_gemma":0.000325822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006841282,"about_ca_topic_score_gemma":0.000003149143,"domain_scores_codex":[0.9970962,0.0001358526,0.00129487,0.0003006499,0.0005221296,0.0006502305],"domain_scores_gemma":[0.9980095,0.0005095467,0.0004675484,0.0006107911,0.0002475246,0.0001550987],"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":[0.00003506745,0.0001316639,0.000008288287,0.00007847268,0.0002167331,5.533994e-7,0.0009714962,0.9637166,0.00002194602,0.0006504342,0.0001453461,0.03402338],"study_design_scores_gemma":[0.00382042,0.0001360429,0.000001508408,0.0001243982,0.0001307534,0.00000831902,0.0005675602,0.9915382,0.001424603,0.000008754128,0.001897955,0.0003415288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003712113,0.00001408139,0.9932142,0.00005561432,0.002454965,0.001706723,0.000009116203,0.0004757128,0.001698325],"genre_scores_gemma":[0.8222142,0.000007722354,0.1767377,0.0001725246,0.0001455963,0.0002882322,0.00002170138,0.00002487178,0.0003874458],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.821843,"threshold_uncertainty_score":0.999868,"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."}}