Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288357413> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4288357413 abstract "With the increasing availability of traffic data and advance of deep reinforcement learning techniques, there is an emerging trend of employing reinforcement learning (RL) for traffic signal control. A key question for applying RL to traffic signal control is how to define the reward and state. The ultimate objective in traffic signal control is to minimize the travel time, which is difficult to reach directly. Hence, existing studies often define reward as an ad-hoc weighted linear combination of several traffic measures. However, there is no guarantee that the travel time will be optimized with the reward. In addition, recent RL approaches use more complicated state (e.g., image) in order to describe the full traffic situation. However, none of the existing studies has discussed whether such a complex state representation is necessary. This extra complexity may lead to significantly slower learning process but may not necessarily bring significant performance gain. In this paper, we propose to re-examine the RL approaches through the lens of classic transportation theory. We ask the following questions: (1) How should we design the reward so that one can guarantee to minimize the travel time? (2) How to design a state representation which is concise yet sufficient to obtain the optimal solution? Our proposed method LIT is theoretically supported by the classic traffic signal control methods in transportation field. LIT has a very simple state and reward design, thus can serve as a building block for future RL approaches to traffic signal control. Extensive experiments on both synthetic and real datasets show that our method significantly outperforms the state-of-the-art traffic signal control methods." @default.
- W4288357413 created "2022-07-29" @default.
- W4288357413 creator A5000248352 @default.
- W4288357413 creator A5003021595 @default.
- W4288357413 creator A5016516907 @default.
- W4288357413 creator A5025274226 @default.
- W4288357413 creator A5053725057 @default.
- W4288357413 creator A5067200755 @default.
- W4288357413 creator A5080198603 @default.
- W4288357413 creator A5083876527 @default.
- W4288357413 date "2019-05-12" @default.
- W4288357413 modified "2023-10-17" @default.
- W4288357413 title "Diagnosing Reinforcement Learning for Traffic Signal Control" @default.
- W4288357413 doi "https://doi.org/10.48550/arxiv.1905.04716" @default.
- W4288357413 hasPublicationYear "2019" @default.
- W4288357413 type Work @default.
- W4288357413 citedByCount "0" @default.
- W4288357413 crossrefType "posted-content" @default.
- W4288357413 hasAuthorship W4288357413A5000248352 @default.
- W4288357413 hasAuthorship W4288357413A5003021595 @default.
- W4288357413 hasAuthorship W4288357413A5016516907 @default.
- W4288357413 hasAuthorship W4288357413A5025274226 @default.
- W4288357413 hasAuthorship W4288357413A5053725057 @default.
- W4288357413 hasAuthorship W4288357413A5067200755 @default.
- W4288357413 hasAuthorship W4288357413A5080198603 @default.
- W4288357413 hasAuthorship W4288357413A5083876527 @default.
- W4288357413 hasBestOaLocation W42883574131 @default.
- W4288357413 hasConcept C111919701 @default.
- W4288357413 hasConcept C11413529 @default.
- W4288357413 hasConcept C154945302 @default.
- W4288357413 hasConcept C17744445 @default.
- W4288357413 hasConcept C199360897 @default.
- W4288357413 hasConcept C199539241 @default.
- W4288357413 hasConcept C202444582 @default.
- W4288357413 hasConcept C2524010 @default.
- W4288357413 hasConcept C2775924081 @default.
- W4288357413 hasConcept C2776359362 @default.
- W4288357413 hasConcept C2777210771 @default.
- W4288357413 hasConcept C2779843651 @default.
- W4288357413 hasConcept C33923547 @default.
- W4288357413 hasConcept C41008148 @default.
- W4288357413 hasConcept C48103436 @default.
- W4288357413 hasConcept C94625758 @default.
- W4288357413 hasConcept C9652623 @default.
- W4288357413 hasConcept C97541855 @default.
- W4288357413 hasConcept C98045186 @default.
- W4288357413 hasConceptScore W4288357413C111919701 @default.
- W4288357413 hasConceptScore W4288357413C11413529 @default.
- W4288357413 hasConceptScore W4288357413C154945302 @default.
- W4288357413 hasConceptScore W4288357413C17744445 @default.
- W4288357413 hasConceptScore W4288357413C199360897 @default.
- W4288357413 hasConceptScore W4288357413C199539241 @default.
- W4288357413 hasConceptScore W4288357413C202444582 @default.
- W4288357413 hasConceptScore W4288357413C2524010 @default.
- W4288357413 hasConceptScore W4288357413C2775924081 @default.
- W4288357413 hasConceptScore W4288357413C2776359362 @default.
- W4288357413 hasConceptScore W4288357413C2777210771 @default.
- W4288357413 hasConceptScore W4288357413C2779843651 @default.
- W4288357413 hasConceptScore W4288357413C33923547 @default.
- W4288357413 hasConceptScore W4288357413C41008148 @default.
- W4288357413 hasConceptScore W4288357413C48103436 @default.
- W4288357413 hasConceptScore W4288357413C94625758 @default.
- W4288357413 hasConceptScore W4288357413C9652623 @default.
- W4288357413 hasConceptScore W4288357413C97541855 @default.
- W4288357413 hasConceptScore W4288357413C98045186 @default.
- W4288357413 hasLocation W42883574131 @default.
- W4288357413 hasOpenAccess W4288357413 @default.
- W4288357413 hasPrimaryLocation W42883574131 @default.
- W4288357413 hasRelatedWork W1562959674 @default.
- W4288357413 hasRelatedWork W2923653485 @default.
- W4288357413 hasRelatedWork W2932992352 @default.
- W4288357413 hasRelatedWork W2952472710 @default.
- W4288357413 hasRelatedWork W2957776456 @default.
- W4288357413 hasRelatedWork W3209094908 @default.
- W4288357413 hasRelatedWork W4210912933 @default.
- W4288357413 hasRelatedWork W4255994452 @default.
- W4288357413 hasRelatedWork W4361026739 @default.
- W4288357413 hasRelatedWork W4372194388 @default.
- W4288357413 isParatext "false" @default.
- W4288357413 isRetracted "false" @default.
- W4288357413 workType "article" @default.