FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296704755> ?p ?o ?g. }

• W4296704755 endingPage "24007" @default.
• W4296704755 startingPage "23993" @default.
• W4296704755 abstract "This study presents a robust deep reinforcement learning (RL) approach for real-time, network-wide holding control with transfer synchronization, considering stochastic passenger demand and vehicle running time during daily operations. The problem is formulated within a multi-agent RL framework where each active trip is considered as an agent, which not only interacts with the environment but also with other agents in the considered transit network. A specific learning procedure is developed to learn robust policies by introducing <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$maxmin$ </tex-math></inline-formula> optimization into the learning objective. The agents are trained via deep deterministic policy gradient algorithm (DDPG) using an extended actor-critic framework with a joint action approximator. The effectiveness of the proposed approach is evaluated in a simulator, which is calibrated using data collected from a transit network in Twin Cities Minnesota, USA. The learned policy is compared with no control, rule-based control and the rolling horizon optimization control (RHOC). Computational results suggest that RL approach can significantly reduce the online computation time by about 50% compared with RHOC. In terms of policy performance, under deterministic scenario, the average waiting time of RL approach is 1.3% higher than the theoretical lower bound of average waiting time; under stochastic scenarios, RL approach could reduce as much as 18% average waiting time than RHOC, and the performance relative to RHOC improves when the level of system uncertainty increases. Evaluation under disrupted environment also suggests that the proposed RL method is more robust against short term uncertainties. The promising results in terms of both online computational efficiency and solution effectiveness suggest that the proposed RL method is a valid candidate for real-time transit control when the dynamics cannot be modeled perfectly with system uncertainties, as is the case for the network-wide transfer synchronization problem." @default.
• W4296704755 created "2022-09-23" @default.
• W4296704755 creator A5011986626 @default.
• W4296704755 creator A5041242808 @default.
• W4296704755 creator A5073534534 @default.
• W4296704755 creator A5086957398 @default.
• W4296704755 creator A5087813798 @default.
• W4296704755 date "2022-12-01" @default.
• W4296704755 modified "2023-10-15" @default.
• W4296704755 title "Real-Time Holding Control for Transfer Synchronization via Robust Multiagent Reinforcement Learning" @default.
• W4296704755 cites W1972922866 @default.
• W4296704755 cites W1975881942 @default.
• W4296704755 cites W1981562949 @default.
• W4296704755 cites W2053362634 @default.
• W4296704755 cites W2104700613 @default.
• W4296704755 cites W2144978534 @default.
• W4296704755 cites W2145339207 @default.
• W4296704755 cites W2174113592 @default.
• W4296704755 cites W2257979135 @default.
• W4296704755 cites W2337033248 @default.
• W4296704755 cites W2513786868 @default.
• W4296704755 cites W2552737632 @default.
• W4296704755 cites W2564320642 @default.
• W4296704755 cites W2575705757 @default.
• W4296704755 cites W2580712508 @default.
• W4296704755 cites W2604885728 @default.
• W4296704755 cites W2617547828 @default.
• W4296704755 cites W2626836525 @default.
• W4296704755 cites W2740333758 @default.
• W4296704755 cites W2747500309 @default.
• W4296704755 cites W2793570951 @default.
• W4296704755 cites W2794811985 @default.
• W4296704755 cites W2811245469 @default.
• W4296704755 cites W2890110970 @default.
• W4296704755 cites W2904455790 @default.
• W4296704755 cites W2904681300 @default.
• W4296704755 cites W2913943913 @default.
• W4296704755 cites W2944023643 @default.
• W4296704755 cites W2954943310 @default.
• W4296704755 cites W2974835507 @default.
• W4296704755 cites W2987754653 @default.
• W4296704755 cites W2997058333 @default.
• W4296704755 cites W3008688678 @default.
• W4296704755 cites W3021479140 @default.
• W4296704755 cites W3027102885 @default.
• W4296704755 cites W3044015199 @default.
• W4296704755 cites W3084058509 @default.
• W4296704755 cites W3096227293 @default.
• W4296704755 cites W3101442004 @default.
• W4296704755 cites W3155225979 @default.
• W4296704755 cites W598095728 @default.
• W4296704755 doi "https://doi.org/10.1109/tits.2022.3204805" @default.
• W4296704755 hasPublicationYear "2022" @default.
• W4296704755 type Work @default.
• W4296704755 citedByCount "1" @default.
• W4296704755 countsByYear W42967047552023 @default.
• W4296704755 crossrefType "journal-article" @default.
• W4296704755 hasAuthorship W4296704755A5011986626 @default.
• W4296704755 hasAuthorship W4296704755A5041242808 @default.
• W4296704755 hasAuthorship W4296704755A5073534534 @default.
• W4296704755 hasAuthorship W4296704755A5086957398 @default.
• W4296704755 hasAuthorship W4296704755A5087813798 @default.
• W4296704755 hasConcept C105795698 @default.
• W4296704755 hasConcept C126255220 @default.
• W4296704755 hasConcept C127162648 @default.
• W4296704755 hasConcept C154945302 @default.
• W4296704755 hasConcept C2778562939 @default.
• W4296704755 hasConcept C31258907 @default.
• W4296704755 hasConcept C33923547 @default.
• W4296704755 hasConcept C41008148 @default.
• W4296704755 hasConcept C55689738 @default.
• W4296704755 hasConcept C97541855 @default.
• W4296704755 hasConceptScore W4296704755C105795698 @default.
• W4296704755 hasConceptScore W4296704755C126255220 @default.
• W4296704755 hasConceptScore W4296704755C127162648 @default.
• W4296704755 hasConceptScore W4296704755C154945302 @default.
• W4296704755 hasConceptScore W4296704755C2778562939 @default.
• W4296704755 hasConceptScore W4296704755C31258907 @default.
• W4296704755 hasConceptScore W4296704755C33923547 @default.
• W4296704755 hasConceptScore W4296704755C41008148 @default.
• W4296704755 hasConceptScore W4296704755C55689738 @default.
• W4296704755 hasConceptScore W4296704755C97541855 @default.
• W4296704755 hasFunder F4320306076 @default.
• W4296704755 hasFunder F4320308171 @default.
• W4296704755 hasFunder F4320321001 @default.
• W4296704755 hasFunder F4320322769 @default.
• W4296704755 hasIssue "12" @default.
• W4296704755 hasLocation W42967047551 @default.
• W4296704755 hasOpenAccess W4296704755 @default.
• W4296704755 hasPrimaryLocation W42967047551 @default.
• W4296704755 hasRelatedWork W2923653485 @default.
• W4296704755 hasRelatedWork W2952472710 @default.
• W4296704755 hasRelatedWork W2957776456 @default.
• W4296704755 hasRelatedWork W3005560120 @default.
• W4296704755 hasRelatedWork W3037422413 @default.
• W4296704755 hasRelatedWork W4206669594 @default.
• W4296704755 hasRelatedWork W4224287422 @default.
• W4296704755 hasRelatedWork W4255994452 @default.

• next