{"id":"W4415054220","doi":"10.1016/j.oceaneng.2025.123056","title":"Value decomposition reinforcement learning-based formation control for multi-USVs with incomplete information","year":2025,"lang":"en","type":"article","venue":"Ocean Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Shanghai Municipal Education Commission; National Natural Science Foundation of China; Natural Science Foundation of Shanghai","keywords":"Control theory (sociology); Reinforcement learning; Complete information; Convergence (economics); Controller (irrigation); Kalman filter; Position (finance); Filter (signal processing); Observer (physics); Decomposition","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":[],"consensus_categories":[],"category_scores_codex":[0.0002673844,0.0001571406,0.0001633385,0.000260047,0.0001354752,0.0001599567,0.0002777263,0.00004553298,5.135682e-7],"category_scores_gemma":[0.00007502497,0.0001518031,0.00005588611,0.0002462331,0.00001114709,0.001150565,0.00003574472,0.0001203542,0.000003981688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002019674,"about_ca_system_score_gemma":0.00005103378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007667441,"about_ca_topic_score_gemma":0.000001456556,"domain_scores_codex":[0.9991328,0.00001812738,0.0002849075,0.0001433917,0.00015665,0.0002641726],"domain_scores_gemma":[0.9993566,0.0001076656,0.0001241257,0.0002069063,0.0001582862,0.00004637455],"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":[0.00003430022,0.00001028708,0.0000533142,0.00007210282,0.00002765679,5.890569e-7,0.00009983526,0.9654301,0.0001607146,0.02779006,0.00002361158,0.006297379],"study_design_scores_gemma":[0.002827184,0.0001665922,0.0004027158,0.00009508053,0.000017695,0.000002187878,0.000008791035,0.9921465,0.0005115975,0.0000317332,0.00362827,0.0001616891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001132016,0.00001594258,0.997313,0.0002427144,0.0001234018,0.0007343823,0.000003270472,0.0003901658,0.00004516641],"genre_scores_gemma":[0.8307261,4.417952e-7,0.1688832,0.0002218811,0.00001269655,0.00005820089,0.00006854849,0.00000723754,0.00002169057],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8295941,"threshold_uncertainty_score":0.619035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005645907648123808,"score_gpt":0.2225336120687537,"score_spread":0.2168877044206299,"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."}}