Matches in SemOpenAlex for { <https://semopenalex.org/work/W2374550006> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2374550006 abstract "The main contribution of this paper is to implement a hybrid method of coordination from the combinationof interaction models developed previously. The interaction models are based on the sharing of rewards forlearning with multiple agents in order to discover interactively good quality policies. Exchange of rewardsamong agents, when not occur properly, can cause delays in learning or even cause unexpected behavior,making the cooperation inefficient and converging to a non-satisfactory policy. From these concepts, thehybrid method uses the characteristics of each model, reducing possible conflicts between different policyactions with rewards, improving the coordination of agents in reinforcement learning problems. Experimentalresults show that the hybrid method can accelerate the convergence, rapidly gaining optimal policieseven in large spaces of states, exceeding the results of classical approaches to reinforcement learning." @default.
- W2374550006 created "2016-06-24" @default.
- W2374550006 creator A5003807083 @default.
- W2374550006 creator A5008491503 @default.
- W2374550006 creator A5030200528 @default.
- W2374550006 creator A5035426257 @default.
- W2374550006 creator A5039827669 @default.
- W2374550006 creator A5052190642 @default.
- W2374550006 date "2016-01-01" @default.
- W2374550006 modified "2023-10-17" @default.
- W2374550006 title "A Hybrid Interaction Model for Multi-Agent Reinforcement Learning" @default.
- W2374550006 cites W1515308897 @default.
- W2374550006 cites W1540725368 @default.
- W2374550006 cites W1570469988 @default.
- W2374550006 cites W171723243 @default.
- W2374550006 cites W1759988108 @default.
- W2374550006 cites W1984087082 @default.
- W2374550006 cites W2025406794 @default.
- W2374550006 cites W2098280298 @default.
- W2374550006 cites W2107726111 @default.
- W2374550006 cites W2121863487 @default.
- W2374550006 cites W2131376880 @default.
- W2374550006 cites W2147492008 @default.
- W2374550006 cites W2152576222 @default.
- W2374550006 cites W2189058185 @default.
- W2374550006 cites W2250340166 @default.
- W2374550006 cites W2276827050 @default.
- W2374550006 cites W2971274224 @default.
- W2374550006 doi "https://doi.org/10.5220/0005832300540061" @default.
- W2374550006 hasPublicationYear "2016" @default.
- W2374550006 type Work @default.
- W2374550006 sameAs 2374550006 @default.
- W2374550006 citedByCount "0" @default.
- W2374550006 crossrefType "proceedings-article" @default.
- W2374550006 hasAuthorship W2374550006A5003807083 @default.
- W2374550006 hasAuthorship W2374550006A5008491503 @default.
- W2374550006 hasAuthorship W2374550006A5030200528 @default.
- W2374550006 hasAuthorship W2374550006A5035426257 @default.
- W2374550006 hasAuthorship W2374550006A5039827669 @default.
- W2374550006 hasAuthorship W2374550006A5052190642 @default.
- W2374550006 hasBestOaLocation W23745500061 @default.
- W2374550006 hasConcept C10138342 @default.
- W2374550006 hasConcept C111472728 @default.
- W2374550006 hasConcept C138885662 @default.
- W2374550006 hasConcept C154945302 @default.
- W2374550006 hasConcept C162324750 @default.
- W2374550006 hasConcept C182306322 @default.
- W2374550006 hasConcept C2777303404 @default.
- W2374550006 hasConcept C2779530757 @default.
- W2374550006 hasConcept C41008148 @default.
- W2374550006 hasConcept C50522688 @default.
- W2374550006 hasConcept C97541855 @default.
- W2374550006 hasConceptScore W2374550006C10138342 @default.
- W2374550006 hasConceptScore W2374550006C111472728 @default.
- W2374550006 hasConceptScore W2374550006C138885662 @default.
- W2374550006 hasConceptScore W2374550006C154945302 @default.
- W2374550006 hasConceptScore W2374550006C162324750 @default.
- W2374550006 hasConceptScore W2374550006C182306322 @default.
- W2374550006 hasConceptScore W2374550006C2777303404 @default.
- W2374550006 hasConceptScore W2374550006C2779530757 @default.
- W2374550006 hasConceptScore W2374550006C41008148 @default.
- W2374550006 hasConceptScore W2374550006C50522688 @default.
- W2374550006 hasConceptScore W2374550006C97541855 @default.
- W2374550006 hasLocation W23745500061 @default.
- W2374550006 hasOpenAccess W2374550006 @default.
- W2374550006 hasPrimaryLocation W23745500061 @default.
- W2374550006 hasRelatedWork W1457482454 @default.
- W2374550006 hasRelatedWork W1511570998 @default.
- W2374550006 hasRelatedWork W1562437701 @default.
- W2374550006 hasRelatedWork W2168438882 @default.
- W2374550006 hasRelatedWork W2327142188 @default.
- W2374550006 hasRelatedWork W2349158267 @default.
- W2374550006 hasRelatedWork W2435642473 @default.
- W2374550006 hasRelatedWork W2501699293 @default.
- W2374550006 hasRelatedWork W2756139227 @default.
- W2374550006 hasRelatedWork W2808546214 @default.
- W2374550006 hasRelatedWork W2978070926 @default.
- W2374550006 hasRelatedWork W2978405293 @default.
- W2374550006 hasRelatedWork W2978964352 @default.
- W2374550006 hasRelatedWork W3003032574 @default.
- W2374550006 hasRelatedWork W3012532100 @default.
- W2374550006 hasRelatedWork W3037941652 @default.
- W2374550006 hasRelatedWork W3081310128 @default.
- W2374550006 hasRelatedWork W3082811381 @default.
- W2374550006 hasRelatedWork W3096351713 @default.
- W2374550006 hasRelatedWork W2967490577 @default.
- W2374550006 isParatext "false" @default.
- W2374550006 isRetracted "false" @default.
- W2374550006 magId "2374550006" @default.
- W2374550006 workType "article" @default.