{"id":"W4416642639","doi":"10.1016/j.engappai.2025.113308","title":"A hybrid deep reinforcement learning approach for target allocation and routing of multiple nonholonomic vehicles","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Nexen (Canada)","funders":"Defense Acquisition Program Administration; Korea University; Korea Research Institute for Defense Technology Planning and Advancement","keywords":"Routing (electronic design automation); Travelling salesman problem; Scalability; Reinforcement learning; Constraint (computer-aided design); 2-opt; Vehicle routing problem; Artificial neural network","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":[0.0003449748,0.00009426978,0.0001530871,0.000165542,0.00008243223,0.00002763026,0.0003633676,0.0000329126,2.825694e-7],"category_scores_gemma":[0.0001933555,0.0001098851,0.00003555893,0.0002688919,0.00003860308,0.0001002409,0.00009645783,0.00008795835,9.307434e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002869775,"about_ca_system_score_gemma":0.00003231239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002251463,"about_ca_topic_score_gemma":1.401147e-7,"domain_scores_codex":[0.9991055,0.00001020918,0.0004074061,0.0002470773,0.00008209004,0.0001477124],"domain_scores_gemma":[0.999189,0.0002559402,0.000138927,0.0002773719,0.0001094875,0.00002926661],"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":[0.000002997435,0.00002509822,0.00008240234,0.00006890428,0.00001344433,3.610963e-8,0.0002389867,0.8979123,0.006977523,0.05530724,0.000001715897,0.0393694],"study_design_scores_gemma":[0.00002287525,0.00002495296,0.00009111367,0.00002734695,0.000006321472,7.790255e-7,0.00005277387,0.8952878,0.1033316,0.001040737,0.00003866368,0.0000750389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003256737,0.0001141891,0.9959724,0.00004654849,0.00004240845,0.0004330148,0.000001236904,0.00007655558,0.0000569143],"genre_scores_gemma":[0.5502282,0.000003829644,0.4496112,0.00000290021,0.00001066431,0.0001235523,0.000006771132,0.00000369294,0.00000917641],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5469714,"threshold_uncertainty_score":0.4480985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01768247485987009,"score_gpt":0.2533664730991669,"score_spread":0.2356839982392968,"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."}}