Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378501680> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4378501680 abstract "Many recent works have turned to multi-agent reinforcement learning (MARL) for adaptive traffic signal control to optimize the travel time of vehicles over large urban networks. However, achieving effective and scalable cooperation among junctions (agents) remains an open challenge, as existing methods often rely on extensive, non-generalizable reward shaping or on non-scalable centralized learning. To address these problems, we propose a new MARL method for traffic signal control, SocialLight, which learns cooperative traffic control policies by distributedly estimating the individual marginal contribution of agents on their local neighborhood. SocialLight relies on the Asynchronous Actor Critic (A3C) framework, and makes learning scalable by learning a locally-centralized critic conditioned over the states and actions of neighboring agents, used by agents to estimate individual contributions by counterfactual reasoning. We further introduce important modifications to the advantage calculation that help stabilize policy updates. These modifications decouple the impact of the neighbors' actions on the computed advantages, thereby reducing the variance in the gradient updates. We benchmark our trained network against state-of-the-art traffic signal control methods on standard benchmarks in two traffic simulators, SUMO and CityFlow. Our results show that SocialLight exhibits improved scalability to larger road networks and better performance across usual traffic metrics." @default.
- W4378501680 created "2023-05-27" @default.
- W4378501680 creator A5019190057 @default.
- W4378501680 creator A5040083642 @default.
- W4378501680 creator A5069667034 @default.
- W4378501680 creator A5079131511 @default.
- W4378501680 date "2023-04-20" @default.
- W4378501680 modified "2023-09-25" @default.
- W4378501680 title "SocialLight: Distributed Cooperation Learning towards Network-Wide Traffic Signal Control" @default.
- W4378501680 doi "https://doi.org/10.48550/arxiv.2305.16145" @default.
- W4378501680 hasPublicationYear "2023" @default.
- W4378501680 type Work @default.
- W4378501680 citedByCount "0" @default.
- W4378501680 crossrefType "posted-content" @default.
- W4378501680 hasAuthorship W4378501680A5019190057 @default.
- W4378501680 hasAuthorship W4378501680A5040083642 @default.
- W4378501680 hasAuthorship W4378501680A5069667034 @default.
- W4378501680 hasAuthorship W4378501680A5079131511 @default.
- W4378501680 hasBestOaLocation W43785016801 @default.
- W4378501680 hasConcept C108650721 @default.
- W4378501680 hasConcept C111472728 @default.
- W4378501680 hasConcept C120314980 @default.
- W4378501680 hasConcept C13280743 @default.
- W4378501680 hasConcept C138885662 @default.
- W4378501680 hasConcept C151319957 @default.
- W4378501680 hasConcept C154945302 @default.
- W4378501680 hasConcept C185798385 @default.
- W4378501680 hasConcept C199360897 @default.
- W4378501680 hasConcept C205649164 @default.
- W4378501680 hasConcept C2775924081 @default.
- W4378501680 hasConcept C2779843651 @default.
- W4378501680 hasConcept C31258907 @default.
- W4378501680 hasConcept C41008148 @default.
- W4378501680 hasConcept C48044578 @default.
- W4378501680 hasConcept C77088390 @default.
- W4378501680 hasConcept C97541855 @default.
- W4378501680 hasConceptScore W4378501680C108650721 @default.
- W4378501680 hasConceptScore W4378501680C111472728 @default.
- W4378501680 hasConceptScore W4378501680C120314980 @default.
- W4378501680 hasConceptScore W4378501680C13280743 @default.
- W4378501680 hasConceptScore W4378501680C138885662 @default.
- W4378501680 hasConceptScore W4378501680C151319957 @default.
- W4378501680 hasConceptScore W4378501680C154945302 @default.
- W4378501680 hasConceptScore W4378501680C185798385 @default.
- W4378501680 hasConceptScore W4378501680C199360897 @default.
- W4378501680 hasConceptScore W4378501680C205649164 @default.
- W4378501680 hasConceptScore W4378501680C2775924081 @default.
- W4378501680 hasConceptScore W4378501680C2779843651 @default.
- W4378501680 hasConceptScore W4378501680C31258907 @default.
- W4378501680 hasConceptScore W4378501680C41008148 @default.
- W4378501680 hasConceptScore W4378501680C48044578 @default.
- W4378501680 hasConceptScore W4378501680C77088390 @default.
- W4378501680 hasConceptScore W4378501680C97541855 @default.
- W4378501680 hasLocation W43785016801 @default.
- W4378501680 hasOpenAccess W4378501680 @default.
- W4378501680 hasPrimaryLocation W43785016801 @default.
- W4378501680 hasRelatedWork W112744582 @default.
- W4378501680 hasRelatedWork W1596201972 @default.
- W4378501680 hasRelatedWork W1967954938 @default.
- W4378501680 hasRelatedWork W1986253068 @default.
- W4378501680 hasRelatedWork W1992807924 @default.
- W4378501680 hasRelatedWork W2364921833 @default.
- W4378501680 hasRelatedWork W2380023786 @default.
- W4378501680 hasRelatedWork W2385146268 @default.
- W4378501680 hasRelatedWork W2789601449 @default.
- W4378501680 hasRelatedWork W2944431808 @default.
- W4378501680 isParatext "false" @default.
- W4378501680 isRetracted "false" @default.
- W4378501680 workType "article" @default.