{"id":"W4386208322","doi":"10.1016/j.trc.2023.104309","title":"Multi-objective multi-agent deep reinforcement learning to reduce bus bunching for multiline services with a shared corridor","year":2023,"lang":"en","type":"article","venue":"Transportation Research Part C Emerging Technologies","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Transit (satellite); Line (geometry); Preference; Control (management); Service (business); Public transport; State (computer science); Real-time computing; Transport engineering; Distributed computing; Engineering; Artificial intelligence; Mathematics; Algorithm","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":[0.0006725637,0.0008676448,0.001116192,0.0004650479,0.0004672198,0.0005812096,0.001272508,0.001047839,0.003003552],"category_scores_gemma":[0.001448683,0.0005194301,0.0005003447,0.0004779655,0.0005054048,0.0009441093,0.001022988,0.001298012,0.0002656912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001095482,"about_ca_system_score_gemma":0.001344193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02193164,"about_ca_topic_score_gemma":0.02733587,"domain_scores_codex":[0.9997422,0.00006519196,0.000008067944,0.00005563765,0.00004119588,0.00008758927],"domain_scores_gemma":[0.9993406,0.0003187932,0.00007508264,0.0000344476,0.0001352901,0.00009577733],"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":[0.0000740101,0.00005858518,0.0003846064,0.00001542838,0.00001663317,0.00003040409,0.00001183424,0.9881591,0.0003762646,0.0006034253,0.0005805977,0.009689154],"study_design_scores_gemma":[0.000002827403,0.000008561181,0.00003053799,7.822892e-7,0.000001905142,0.000001104809,0.000002199868,0.9997308,0.00004329306,0.0001503127,0.0000270197,7.572214e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.261115,0.0005783897,0.7310057,0.0005102658,0.000146156,0.00007402427,0.0002445513,0.001259683,0.005066214],"genre_scores_gemma":[0.9767529,0.0000356363,0.02097602,0.00006852314,0.00001141652,0.00003265801,0.00009631606,0.00003463033,0.001991914],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02193164,"threshold_uncertainty_score":0.04360801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09121428174535277,"score_gpt":0.4053521956462414,"score_spread":0.3141379139008886,"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."}}