Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205408891> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3205408891 endingPage "216" @default.
- W3205408891 startingPage "207" @default.
- W3205408891 abstract "Recent work in multi-agent reinforcement learning has investigated inter agent communication which is learned simultaneously with the action policy in order to improve the team reward. In this paper, we investigate independent Q-learning (IQL) without communication and differentiable inter-agent learning (DIAL) with learned communication on an adaptive traffic control system (ATCS). In real world ATCS, it is impossible to present the full state of the environment to every agent so in our simulation, the individual agents will only have a limited observation of the full state of the environment. The ATCS will be simulated using the Simulation of Urban MObility (SUMO) traffic simulator in which two connected intersections are simulated. Every intersection is controlled by an agent which has the ability to change the direction of the traffic flow. Our results show that a DIAL agent outperforms an independent Q-learner on both training time and on maximum achieved reward as it is able to share relevant information with the other agents." @default.
- W3205408891 created "2021-10-25" @default.
- W3205408891 creator A5008171683 @default.
- W3205408891 creator A5008424099 @default.
- W3205408891 creator A5015248763 @default.
- W3205408891 creator A5041138120 @default.
- W3205408891 creator A5049021976 @default.
- W3205408891 creator A5074520540 @default.
- W3205408891 creator A5084961388 @default.
- W3205408891 creator A5085371582 @default.
- W3205408891 date "2021-10-20" @default.
- W3205408891 modified "2023-09-23" @default.
- W3205408891 title "Learning to Communicate with Reinforcement Learning for an Adaptive Traffic Control System" @default.
- W3205408891 cites W1543115993 @default.
- W3205408891 cites W1641379095 @default.
- W3205408891 cites W2088595989 @default.
- W3205408891 cites W2747213132 @default.
- W3205408891 cites W2903709398 @default.
- W3205408891 cites W2933570795 @default.
- W3205408891 cites W2980784261 @default.
- W3205408891 doi "https://doi.org/10.1007/978-3-030-89899-1_21" @default.
- W3205408891 hasPublicationYear "2021" @default.
- W3205408891 type Work @default.
- W3205408891 sameAs 3205408891 @default.
- W3205408891 citedByCount "0" @default.
- W3205408891 crossrefType "book-chapter" @default.
- W3205408891 hasAuthorship W3205408891A5008171683 @default.
- W3205408891 hasAuthorship W3205408891A5008424099 @default.
- W3205408891 hasAuthorship W3205408891A5015248763 @default.
- W3205408891 hasAuthorship W3205408891A5041138120 @default.
- W3205408891 hasAuthorship W3205408891A5049021976 @default.
- W3205408891 hasAuthorship W3205408891A5074520540 @default.
- W3205408891 hasAuthorship W3205408891A5084961388 @default.
- W3205408891 hasAuthorship W3205408891A5085371582 @default.
- W3205408891 hasBestOaLocation W32054088912 @default.
- W3205408891 hasConcept C11413529 @default.
- W3205408891 hasConcept C120314980 @default.
- W3205408891 hasConcept C121332964 @default.
- W3205408891 hasConcept C127413603 @default.
- W3205408891 hasConcept C154945302 @default.
- W3205408891 hasConcept C207512268 @default.
- W3205408891 hasConcept C22212356 @default.
- W3205408891 hasConcept C2775924081 @default.
- W3205408891 hasConcept C2780791683 @default.
- W3205408891 hasConcept C31258907 @default.
- W3205408891 hasConcept C41008148 @default.
- W3205408891 hasConcept C41550386 @default.
- W3205408891 hasConcept C44154836 @default.
- W3205408891 hasConcept C48103436 @default.
- W3205408891 hasConcept C62520636 @default.
- W3205408891 hasConcept C64543145 @default.
- W3205408891 hasConcept C97541855 @default.
- W3205408891 hasConceptScore W3205408891C11413529 @default.
- W3205408891 hasConceptScore W3205408891C120314980 @default.
- W3205408891 hasConceptScore W3205408891C121332964 @default.
- W3205408891 hasConceptScore W3205408891C127413603 @default.
- W3205408891 hasConceptScore W3205408891C154945302 @default.
- W3205408891 hasConceptScore W3205408891C207512268 @default.
- W3205408891 hasConceptScore W3205408891C22212356 @default.
- W3205408891 hasConceptScore W3205408891C2775924081 @default.
- W3205408891 hasConceptScore W3205408891C2780791683 @default.
- W3205408891 hasConceptScore W3205408891C31258907 @default.
- W3205408891 hasConceptScore W3205408891C41008148 @default.
- W3205408891 hasConceptScore W3205408891C41550386 @default.
- W3205408891 hasConceptScore W3205408891C44154836 @default.
- W3205408891 hasConceptScore W3205408891C48103436 @default.
- W3205408891 hasConceptScore W3205408891C62520636 @default.
- W3205408891 hasConceptScore W3205408891C64543145 @default.
- W3205408891 hasConceptScore W3205408891C97541855 @default.
- W3205408891 hasLocation W32054088911 @default.
- W3205408891 hasLocation W32054088912 @default.
- W3205408891 hasOpenAccess W3205408891 @default.
- W3205408891 hasPrimaryLocation W32054088911 @default.
- W3205408891 hasRelatedWork W2404992998 @default.
- W3205408891 hasRelatedWork W2766710212 @default.
- W3205408891 hasRelatedWork W3044695623 @default.
- W3205408891 hasRelatedWork W3093139241 @default.
- W3205408891 hasRelatedWork W3100995593 @default.
- W3205408891 hasRelatedWork W3171195115 @default.
- W3205408891 hasRelatedWork W4287120734 @default.
- W3205408891 hasRelatedWork W4297983614 @default.
- W3205408891 hasRelatedWork W4313396601 @default.
- W3205408891 hasRelatedWork W4321637177 @default.
- W3205408891 isParatext "false" @default.
- W3205408891 isRetracted "false" @default.
- W3205408891 magId "3205408891" @default.
- W3205408891 workType "book-chapter" @default.