Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947287992> ?p ?o ?g. }
- W2947287992 abstract "Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other methods of training an individual, discrete policy for each agent and then enforcing cooperation through some additional inter-policy mechanism, we follow the spirit of recent work on the power of relational inductive biases in deep networks by learning multi-agent relationships at the policy level via an attentional architecture. In our method, all agents share the same policy, but independently apply it in their own context to aggregate the other agents' state information when selecting their next action. The structure of our architectures allow them to be applied on environments with varying numbers of agents. We demonstrate our architecture on a benchmark multi-agent autonomous vehicle coordination problem, obtaining superior results to a full-knowledge, fully-centralized reference solution, and significantly outperforming it when scaling to large numbers of agents." @default.
- W2947287992 created "2019-06-07" @default.
- W2947287992 creator A5002745879 @default.
- W2947287992 creator A5078466681 @default.
- W2947287992 date "2019-05-31" @default.
- W2947287992 modified "2023-09-27" @default.
- W2947287992 title "Attentional Policies for Cross-Context Multi-Agent Reinforcement Learning" @default.
- W2947287992 cites W1869778509 @default.
- W2947287992 cites W1902237438 @default.
- W2947287992 cites W1965455100 @default.
- W2947287992 cites W2147492008 @default.
- W2947287992 cites W2257979135 @default.
- W2947287992 cites W2276329747 @default.
- W2947287992 cites W2395575420 @default.
- W2947287992 cites W2564324149 @default.
- W2947287992 cites W2617547828 @default.
- W2947287992 cites W2623431351 @default.
- W2947287992 cites W2626637010 @default.
- W2947287992 cites W2736601468 @default.
- W2947287992 cites W2756196406 @default.
- W2947287992 cites W2766413382 @default.
- W2947287992 cites W2766447205 @default.
- W2947287992 cites W2794643322 @default.
- W2947287992 cites W2805516822 @default.
- W2947287992 cites W2889986919 @default.
- W2947287992 cites W2895865957 @default.
- W2947287992 cites W2899076365 @default.
- W2947287992 cites W2962966033 @default.
- W2947287992 cites W2963000099 @default.
- W2947287992 cites W2963094322 @default.
- W2947287992 cites W2963184621 @default.
- W2947287992 cites W2963390429 @default.
- W2947287992 cites W2963403868 @default.
- W2947287992 cites W2963407617 @default.
- W2947287992 cites W2963562809 @default.
- W2947287992 cites W2963641140 @default.
- W2947287992 cites W2963717208 @default.
- W2947287992 cites W2963864421 @default.
- W2947287992 cites W2963881016 @default.
- W2947287992 cites W2963925437 @default.
- W2947287992 cites W2964308564 @default.
- W2947287992 cites W2964338167 @default.
- W2947287992 cites W2977639220 @default.
- W2947287992 cites W3093287223 @default.
- W2947287992 cites W36434594 @default.
- W2947287992 hasPublicationYear "2019" @default.
- W2947287992 type Work @default.
- W2947287992 sameAs 2947287992 @default.
- W2947287992 citedByCount "1" @default.
- W2947287992 countsByYear W29472879922020 @default.
- W2947287992 crossrefType "posted-content" @default.
- W2947287992 hasAuthorship W2947287992A5002745879 @default.
- W2947287992 hasAuthorship W2947287992A5078466681 @default.
- W2947287992 hasConcept C119857082 @default.
- W2947287992 hasConcept C123657996 @default.
- W2947287992 hasConcept C13280743 @default.
- W2947287992 hasConcept C13687954 @default.
- W2947287992 hasConcept C137703981 @default.
- W2947287992 hasConcept C142362112 @default.
- W2947287992 hasConcept C151730666 @default.
- W2947287992 hasConcept C153349607 @default.
- W2947287992 hasConcept C154945302 @default.
- W2947287992 hasConcept C159985019 @default.
- W2947287992 hasConcept C185798385 @default.
- W2947287992 hasConcept C192562407 @default.
- W2947287992 hasConcept C205649164 @default.
- W2947287992 hasConcept C2779343474 @default.
- W2947287992 hasConcept C41008148 @default.
- W2947287992 hasConcept C41550386 @default.
- W2947287992 hasConcept C4679612 @default.
- W2947287992 hasConcept C50644808 @default.
- W2947287992 hasConcept C86803240 @default.
- W2947287992 hasConcept C97541855 @default.
- W2947287992 hasConceptScore W2947287992C119857082 @default.
- W2947287992 hasConceptScore W2947287992C123657996 @default.
- W2947287992 hasConceptScore W2947287992C13280743 @default.
- W2947287992 hasConceptScore W2947287992C13687954 @default.
- W2947287992 hasConceptScore W2947287992C137703981 @default.
- W2947287992 hasConceptScore W2947287992C142362112 @default.
- W2947287992 hasConceptScore W2947287992C151730666 @default.
- W2947287992 hasConceptScore W2947287992C153349607 @default.
- W2947287992 hasConceptScore W2947287992C154945302 @default.
- W2947287992 hasConceptScore W2947287992C159985019 @default.
- W2947287992 hasConceptScore W2947287992C185798385 @default.
- W2947287992 hasConceptScore W2947287992C192562407 @default.
- W2947287992 hasConceptScore W2947287992C205649164 @default.
- W2947287992 hasConceptScore W2947287992C2779343474 @default.
- W2947287992 hasConceptScore W2947287992C41008148 @default.
- W2947287992 hasConceptScore W2947287992C41550386 @default.
- W2947287992 hasConceptScore W2947287992C4679612 @default.
- W2947287992 hasConceptScore W2947287992C50644808 @default.
- W2947287992 hasConceptScore W2947287992C86803240 @default.
- W2947287992 hasConceptScore W2947287992C97541855 @default.
- W2947287992 hasLocation W29472879921 @default.
- W2947287992 hasOpenAccess W2947287992 @default.
- W2947287992 hasPrimaryLocation W29472879921 @default.
- W2947287992 hasRelatedWork W2576551432 @default.
- W2947287992 hasRelatedWork W2623431351 @default.
- W2947287992 hasRelatedWork W2898567809 @default.
- W2947287992 hasRelatedWork W2909094873 @default.