Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204163294> ?p ?o ?g. }
- W3204163294 abstract "In cooperative multi-agent reinforcement learning (MARL), where agents only have access to partial observations, efficiently leveraging local information is critical. During long-time observations, agents can build textit{awareness} for teammates to alleviate the problem of partial observability. However, previous MARL methods usually neglect this kind of utilization of local information. To address this problem, we propose a novel framework, multi-agent textit{Local INformation Decomposition for Awareness of teammates} (LINDA), with which agents learn to decompose local information and build awareness for each teammate. We model the awareness as stochastic random variables and perform representation learning to ensure the informativeness of awareness representations by maximizing the mutual information between awareness and the actual trajectory of the corresponding agent. LINDA is agnostic to specific algorithms and can be flexibly integrated to different MARL methods. Sufficient experiments show that the proposed framework learns informative awareness from local partial observations for better collaboration and significantly improves the learning performance, especially on challenging tasks." @default.
- W3204163294 created "2021-10-11" @default.
- W3204163294 creator A5010176958 @default.
- W3204163294 creator A5016024688 @default.
- W3204163294 creator A5016543916 @default.
- W3204163294 creator A5017781290 @default.
- W3204163294 creator A5024197542 @default.
- W3204163294 creator A5048974354 @default.
- W3204163294 creator A5073912249 @default.
- W3204163294 date "2021-09-26" @default.
- W3204163294 modified "2023-09-27" @default.
- W3204163294 title "LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates" @default.
- W3204163294 cites W103885025 @default.
- W3204163294 cites W1518858799 @default.
- W3204163294 cites W1972120293 @default.
- W3204163294 cites W2012812921 @default.
- W3204163294 cites W2099618002 @default.
- W3204163294 cites W2157331557 @default.
- W3204163294 cites W2187089797 @default.
- W3204163294 cites W2292533394 @default.
- W3204163294 cites W2557579533 @default.
- W3204163294 cites W2623431351 @default.
- W3204163294 cites W2626637010 @default.
- W3204163294 cites W2747213132 @default.
- W3204163294 cites W2749807327 @default.
- W3204163294 cites W2786572318 @default.
- W3204163294 cites W2904675649 @default.
- W3204163294 cites W2946606218 @default.
- W3204163294 cites W2951984055 @default.
- W3204163294 cites W2962938168 @default.
- W3204163294 cites W2962966033 @default.
- W3204163294 cites W2963502082 @default.
- W3204163294 cites W2964622232 @default.
- W3204163294 cites W2968526727 @default.
- W3204163294 cites W2979408248 @default.
- W3204163294 cites W3034941755 @default.
- W3204163294 cites W3034971464 @default.
- W3204163294 cites W3035802247 @default.
- W3204163294 cites W3046288222 @default.
- W3204163294 cites W3089778445 @default.
- W3204163294 cites W3091492359 @default.
- W3204163294 cites W3093143205 @default.
- W3204163294 cites W3093287223 @default.
- W3204163294 cites W3093963693 @default.
- W3204163294 cites W3100860002 @default.
- W3204163294 cites W3102824929 @default.
- W3204163294 cites W3104860527 @default.
- W3204163294 cites W3123636359 @default.
- W3204163294 cites W3127463339 @default.
- W3204163294 cites W3156295478 @default.
- W3204163294 cites W3168414797 @default.
- W3204163294 cites W3172310184 @default.
- W3204163294 cites W3187695488 @default.
- W3204163294 cites W3197294986 @default.
- W3204163294 doi "https://doi.org/10.48550/arxiv.2109.12508" @default.
- W3204163294 hasPublicationYear "2021" @default.
- W3204163294 type Work @default.
- W3204163294 sameAs 3204163294 @default.
- W3204163294 citedByCount "0" @default.
- W3204163294 crossrefType "posted-content" @default.
- W3204163294 hasAuthorship W3204163294A5010176958 @default.
- W3204163294 hasAuthorship W3204163294A5016024688 @default.
- W3204163294 hasAuthorship W3204163294A5016543916 @default.
- W3204163294 hasAuthorship W3204163294A5017781290 @default.
- W3204163294 hasAuthorship W3204163294A5024197542 @default.
- W3204163294 hasAuthorship W3204163294A5048974354 @default.
- W3204163294 hasAuthorship W3204163294A5073912249 @default.
- W3204163294 hasBestOaLocation W32041632941 @default.
- W3204163294 hasConcept C107457646 @default.
- W3204163294 hasConcept C119857082 @default.
- W3204163294 hasConcept C124681953 @default.
- W3204163294 hasConcept C152139883 @default.
- W3204163294 hasConcept C154945302 @default.
- W3204163294 hasConcept C17744445 @default.
- W3204163294 hasConcept C18903297 @default.
- W3204163294 hasConcept C199539241 @default.
- W3204163294 hasConcept C2776359362 @default.
- W3204163294 hasConcept C28826006 @default.
- W3204163294 hasConcept C33923547 @default.
- W3204163294 hasConcept C36299963 @default.
- W3204163294 hasConcept C41008148 @default.
- W3204163294 hasConcept C80444323 @default.
- W3204163294 hasConcept C86803240 @default.
- W3204163294 hasConcept C94625758 @default.
- W3204163294 hasConcept C97541855 @default.
- W3204163294 hasConceptScore W3204163294C107457646 @default.
- W3204163294 hasConceptScore W3204163294C119857082 @default.
- W3204163294 hasConceptScore W3204163294C124681953 @default.
- W3204163294 hasConceptScore W3204163294C152139883 @default.
- W3204163294 hasConceptScore W3204163294C154945302 @default.
- W3204163294 hasConceptScore W3204163294C17744445 @default.
- W3204163294 hasConceptScore W3204163294C18903297 @default.
- W3204163294 hasConceptScore W3204163294C199539241 @default.
- W3204163294 hasConceptScore W3204163294C2776359362 @default.
- W3204163294 hasConceptScore W3204163294C28826006 @default.
- W3204163294 hasConceptScore W3204163294C33923547 @default.
- W3204163294 hasConceptScore W3204163294C36299963 @default.
- W3204163294 hasConceptScore W3204163294C41008148 @default.
- W3204163294 hasConceptScore W3204163294C80444323 @default.
- W3204163294 hasConceptScore W3204163294C86803240 @default.