Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283021706> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4283021706 abstract "With the development of sensing and communication technologies in networked cyber-physical systems (CPSs), multi-agent reinforcement learning (MARL)-based methodologies are integrated into the control process of physical systems and demonstrate prominent performance in a wide array of CPS domains, such as connected autonomous vehicles (CAVs). However, it remains challenging to mathematically characterize the improvement of the performance of CAVs with communication and cooperation capability. When each individual autonomous vehicle is originally self-interest, we can not assume that all agents would cooperate naturally during the training process. In this work, we propose to reallocate the system's total reward efficiently to motivate stable cooperation among autonomous vehicles. We formally define and quantify how to reallocate the system's total reward to each agent under the proposed transferable utility game, such that communication-based cooperation among multi-agents increases the system's total reward. We prove that Shapley value-based reward reallocation of MARL locates in the core if the transferable utility game is a convex game. Hence, the cooperation is stable and efficient and the agents should stay in the coalition or the cooperating group. We then propose a cooperative policy learning algorithm with Shapley value reward reallocation. In experiments, compared with several literature algorithms, we show the improvement of the mean episode system reward of CAV systems using our proposed algorithm." @default.
- W4283021706 created "2022-06-18" @default.
- W4283021706 creator A5004639938 @default.
- W4283021706 creator A5004660487 @default.
- W4283021706 creator A5021471823 @default.
- W4283021706 creator A5026925915 @default.
- W4283021706 creator A5055691206 @default.
- W4283021706 date "2022-05-23" @default.
- W4283021706 modified "2023-10-06" @default.
- W4283021706 title "Stable and Efficient Shapley Value-Based Reward Reallocation for Multi-Agent Reinforcement Learning of Autonomous Vehicles" @default.
- W4283021706 cites W1991638565 @default.
- W4283021706 cites W2008082561 @default.
- W4283021706 cites W2023835067 @default.
- W4283021706 cites W2038607592 @default.
- W4283021706 cites W2080988078 @default.
- W4283021706 cites W2123881124 @default.
- W4283021706 cites W2162735718 @default.
- W4283021706 cites W2194775991 @default.
- W4283021706 cites W2307055197 @default.
- W4283021706 cites W2487898712 @default.
- W4283021706 cites W2509583637 @default.
- W4283021706 cites W2617547828 @default.
- W4283021706 cites W2889923199 @default.
- W4283021706 cites W2903720609 @default.
- W4283021706 cites W2904455790 @default.
- W4283021706 cites W2936013143 @default.
- W4283021706 cites W2963676785 @default.
- W4283021706 cites W2968296999 @default.
- W4283021706 cites W2999862950 @default.
- W4283021706 cites W3091691175 @default.
- W4283021706 cites W3102501663 @default.
- W4283021706 cites W3102824929 @default.
- W4283021706 cites W3109790059 @default.
- W4283021706 cites W4211220176 @default.
- W4283021706 doi "https://doi.org/10.1109/icra46639.2022.9811626" @default.
- W4283021706 hasPublicationYear "2022" @default.
- W4283021706 type Work @default.
- W4283021706 citedByCount "5" @default.
- W4283021706 countsByYear W42830217062023 @default.
- W4283021706 crossrefType "proceedings-article" @default.
- W4283021706 hasAuthorship W4283021706A5004639938 @default.
- W4283021706 hasAuthorship W4283021706A5004660487 @default.
- W4283021706 hasAuthorship W4283021706A5021471823 @default.
- W4283021706 hasAuthorship W4283021706A5026925915 @default.
- W4283021706 hasAuthorship W4283021706A5055691206 @default.
- W4283021706 hasBestOaLocation W42830217062 @default.
- W4283021706 hasConcept C111919701 @default.
- W4283021706 hasConcept C120314980 @default.
- W4283021706 hasConcept C144237770 @default.
- W4283021706 hasConcept C154945302 @default.
- W4283021706 hasConcept C177142836 @default.
- W4283021706 hasConcept C199022921 @default.
- W4283021706 hasConcept C2164484 @default.
- W4283021706 hasConcept C33923547 @default.
- W4283021706 hasConcept C41008148 @default.
- W4283021706 hasConcept C41550386 @default.
- W4283021706 hasConcept C76155785 @default.
- W4283021706 hasConcept C97541855 @default.
- W4283021706 hasConcept C98045186 @default.
- W4283021706 hasConceptScore W4283021706C111919701 @default.
- W4283021706 hasConceptScore W4283021706C120314980 @default.
- W4283021706 hasConceptScore W4283021706C144237770 @default.
- W4283021706 hasConceptScore W4283021706C154945302 @default.
- W4283021706 hasConceptScore W4283021706C177142836 @default.
- W4283021706 hasConceptScore W4283021706C199022921 @default.
- W4283021706 hasConceptScore W4283021706C2164484 @default.
- W4283021706 hasConceptScore W4283021706C33923547 @default.
- W4283021706 hasConceptScore W4283021706C41008148 @default.
- W4283021706 hasConceptScore W4283021706C41550386 @default.
- W4283021706 hasConceptScore W4283021706C76155785 @default.
- W4283021706 hasConceptScore W4283021706C97541855 @default.
- W4283021706 hasConceptScore W4283021706C98045186 @default.
- W4283021706 hasFunder F4320306076 @default.
- W4283021706 hasLocation W42830217061 @default.
- W4283021706 hasLocation W42830217062 @default.
- W4283021706 hasOpenAccess W4283021706 @default.
- W4283021706 hasPrimaryLocation W42830217061 @default.
- W4283021706 hasRelatedWork W1487809722 @default.
- W4283021706 hasRelatedWork W1538386239 @default.
- W4283021706 hasRelatedWork W2012494228 @default.
- W4283021706 hasRelatedWork W2232640127 @default.
- W4283021706 hasRelatedWork W2389976360 @default.
- W4283021706 hasRelatedWork W3125328437 @default.
- W4283021706 hasRelatedWork W4235973033 @default.
- W4283021706 hasRelatedWork W4240140868 @default.
- W4283021706 hasRelatedWork W2189455186 @default.
- W4283021706 hasRelatedWork W3122364537 @default.
- W4283021706 isParatext "false" @default.
- W4283021706 isRetracted "false" @default.
- W4283021706 workType "article" @default.