FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3191556308> ?p ?o ?g. }

• W3191556308 abstract "High sample complexity remains a barrier to the application of reinforcement learning (RL), particularly in multi-agent systems. A large body of work has demonstrated that exploration mechanisms based on the principle of optimism under uncertainty can significantly improve the sample efficiency of RL in single agent tasks. This work seeks to understand the role of optimistic exploration in non-cooperative multi-agent settings. We will show that, in zero-sum games, optimistic exploration can cause the learner to waste time sampling parts of the state space that are irrelevant to strategic play, as they can only be reached through cooperation between both players. To address this issue, we introduce a formal notion of strategically efficient exploration in Markov games, and use this to develop two strategically efficient learning algorithms for finite Markov games. We demonstrate that these methods can be significantly more sample efficient than their optimistic counterparts." @default.
• W3191556308 created "2021-08-16" @default.
• W3191556308 creator A5027441885 @default.
• W3191556308 creator A5029561177 @default.
• W3191556308 creator A5048451922 @default.
• W3191556308 creator A5068523166 @default.
• W3191556308 date "2021-07-30" @default.
• W3191556308 modified "2023-09-27" @default.
• W3191556308 title "Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning" @default.
• W3191556308 cites W1542941925 @default.
• W3191556308 cites W1641379095 @default.
• W3191556308 cites W193176855 @default.
• W3191556308 cites W1988526405 @default.
• W3191556308 cites W2017359019 @default.
• W3191556308 cites W2041367235 @default.
• W3191556308 cites W21934178 @default.
• W3191556308 cites W2614839826 @default.
• W3191556308 cites W2947526499 @default.
• W3191556308 cites W2948764111 @default.
• W3191556308 cites W2963049774 @default.
• W3191556308 cites W2963937357 @default.
• W3191556308 cites W2964067469 @default.
• W3191556308 cites W2964083594 @default.
• W3191556308 cites W2974778612 @default.
• W3191556308 cites W2982316857 @default.
• W3191556308 cites W3035454135 @default.
• W3191556308 cites W3100785954 @default.
• W3191556308 hasPublicationYear "2021" @default.
• W3191556308 type Work @default.
• W3191556308 sameAs 3191556308 @default.
• W3191556308 citedByCount "0" @default.
• W3191556308 crossrefType "posted-content" @default.
• W3191556308 hasAuthorship W3191556308A5027441885 @default.
• W3191556308 hasAuthorship W3191556308A5029561177 @default.
• W3191556308 hasAuthorship W3191556308A5048451922 @default.
• W3191556308 hasAuthorship W3191556308A5068523166 @default.
• W3191556308 hasConcept C105795698 @default.
• W3191556308 hasConcept C106131492 @default.
• W3191556308 hasConcept C111919701 @default.
• W3191556308 hasConcept C11413529 @default.
• W3191556308 hasConcept C119857082 @default.
• W3191556308 hasConcept C140779682 @default.
• W3191556308 hasConcept C154945302 @default.
• W3191556308 hasConcept C15744967 @default.
• W3191556308 hasConcept C185592680 @default.
• W3191556308 hasConcept C198531522 @default.
• W3191556308 hasConcept C204017024 @default.
• W3191556308 hasConcept C2778445095 @default.
• W3191556308 hasConcept C2778572836 @default.
• W3191556308 hasConcept C31972630 @default.
• W3191556308 hasConcept C33923547 @default.
• W3191556308 hasConcept C41008148 @default.
• W3191556308 hasConcept C43617362 @default.
• W3191556308 hasConcept C48103436 @default.
• W3191556308 hasConcept C72434380 @default.
• W3191556308 hasConcept C77805123 @default.
• W3191556308 hasConcept C97541855 @default.
• W3191556308 hasConcept C98763669 @default.
• W3191556308 hasConceptScore W3191556308C105795698 @default.
• W3191556308 hasConceptScore W3191556308C106131492 @default.
• W3191556308 hasConceptScore W3191556308C111919701 @default.
• W3191556308 hasConceptScore W3191556308C11413529 @default.
• W3191556308 hasConceptScore W3191556308C119857082 @default.
• W3191556308 hasConceptScore W3191556308C140779682 @default.
• W3191556308 hasConceptScore W3191556308C154945302 @default.
• W3191556308 hasConceptScore W3191556308C15744967 @default.
• W3191556308 hasConceptScore W3191556308C185592680 @default.
• W3191556308 hasConceptScore W3191556308C198531522 @default.
• W3191556308 hasConceptScore W3191556308C204017024 @default.
• W3191556308 hasConceptScore W3191556308C2778445095 @default.
• W3191556308 hasConceptScore W3191556308C2778572836 @default.
• W3191556308 hasConceptScore W3191556308C31972630 @default.
• W3191556308 hasConceptScore W3191556308C33923547 @default.
• W3191556308 hasConceptScore W3191556308C41008148 @default.
• W3191556308 hasConceptScore W3191556308C43617362 @default.
• W3191556308 hasConceptScore W3191556308C48103436 @default.
• W3191556308 hasConceptScore W3191556308C72434380 @default.
• W3191556308 hasConceptScore W3191556308C77805123 @default.
• W3191556308 hasConceptScore W3191556308C97541855 @default.
• W3191556308 hasConceptScore W3191556308C98763669 @default.
• W3191556308 hasLocation W31915563081 @default.
• W3191556308 hasOpenAccess W3191556308 @default.
• W3191556308 hasPrimaryLocation W31915563081 @default.
• W3191556308 hasRelatedWork W1985742288 @default.
• W3191556308 hasRelatedWork W2005043268 @default.
• W3191556308 hasRelatedWork W2009988656 @default.
• W3191556308 hasRelatedWork W206679605 @default.
• W3191556308 hasRelatedWork W2102690504 @default.
• W3191556308 hasRelatedWork W2134281179 @default.
• W3191556308 hasRelatedWork W2160108098 @default.
• W3191556308 hasRelatedWork W2292969843 @default.
• W3191556308 hasRelatedWork W2409817223 @default.
• W3191556308 hasRelatedWork W2947526499 @default.
• W3191556308 hasRelatedWork W2962966033 @default.
• W3191556308 hasRelatedWork W3005850366 @default.
• W3191556308 hasRelatedWork W3039363169 @default.
• W3191556308 hasRelatedWork W3091819112 @default.
• W3191556308 hasRelatedWork W3094863090 @default.
• W3191556308 hasRelatedWork W3098974658 @default.
• W3191556308 hasRelatedWork W3173450624 @default.

• next