Matches in SemOpenAlex for { <https://semopenalex.org/work/W3103171668> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3103171668 abstract "In competitive multi-agent scenarios, the agents try to defeat their opponents by choosing the best response policies. However, non-stationary opponents make it difficult because they can also adapt to the evolved policies and behaviors of the agents. In this paper, we propose a novel Bayesian policy reuse approach for non-stationary opponents. It combines the learning of the best policy, the detection and prediction of the opponent policy, as well as the selection of the optimal response policy. We introduce an eXtended learning classifier system (XCS) for multi-agent reinforcement learning algorithm in Markov games. Besides, we incorporate the opponent models for opponent policy identification and prediction. Furthermore, we propose a novel online policy reuse technique which can accurately and quickly trace the opponents’ policies in tasks with different rewards. We demonstrate the performance of the proposed approach by comparing it with state-of-art existing algorithms in competitive Markov games." @default.
- W3103171668 created "2020-11-23" @default.
- W3103171668 creator A5022499603 @default.
- W3103171668 creator A5033411376 @default.
- W3103171668 creator A5072120380 @default.
- W3103171668 creator A5079526218 @default.
- W3103171668 creator A5083695433 @default.
- W3103171668 date "2020-11-09" @default.
- W3103171668 modified "2023-09-24" @default.
- W3103171668 title "Detecting and Tracing Multi-Strategic Agents with Opponent Modelling and Bayesian Policy Reuse" @default.
- W3103171668 cites W1542941925 @default.
- W3103171668 cites W1980737627 @default.
- W3103171668 cites W1989101984 @default.
- W3103171668 cites W2008809493 @default.
- W3103171668 cites W2115524942 @default.
- W3103171668 cites W2145339207 @default.
- W3103171668 cites W2551398049 @default.
- W3103171668 cites W2965433979 @default.
- W3103171668 cites W778742492 @default.
- W3103171668 doi "https://doi.org/10.1109/iciea48937.2020.9248178" @default.
- W3103171668 hasPublicationYear "2020" @default.
- W3103171668 type Work @default.
- W3103171668 sameAs 3103171668 @default.
- W3103171668 citedByCount "2" @default.
- W3103171668 countsByYear W31031716682021 @default.
- W3103171668 countsByYear W31031716682022 @default.
- W3103171668 crossrefType "proceedings-article" @default.
- W3103171668 hasAuthorship W3103171668A5022499603 @default.
- W3103171668 hasAuthorship W3103171668A5033411376 @default.
- W3103171668 hasAuthorship W3103171668A5072120380 @default.
- W3103171668 hasAuthorship W3103171668A5079526218 @default.
- W3103171668 hasAuthorship W3103171668A5083695433 @default.
- W3103171668 hasConcept C107673813 @default.
- W3103171668 hasConcept C119857082 @default.
- W3103171668 hasConcept C127413603 @default.
- W3103171668 hasConcept C138673069 @default.
- W3103171668 hasConcept C154945302 @default.
- W3103171668 hasConcept C199360897 @default.
- W3103171668 hasConcept C206588197 @default.
- W3103171668 hasConcept C38652104 @default.
- W3103171668 hasConcept C41008148 @default.
- W3103171668 hasConcept C41065033 @default.
- W3103171668 hasConcept C548081761 @default.
- W3103171668 hasConceptScore W3103171668C107673813 @default.
- W3103171668 hasConceptScore W3103171668C119857082 @default.
- W3103171668 hasConceptScore W3103171668C127413603 @default.
- W3103171668 hasConceptScore W3103171668C138673069 @default.
- W3103171668 hasConceptScore W3103171668C154945302 @default.
- W3103171668 hasConceptScore W3103171668C199360897 @default.
- W3103171668 hasConceptScore W3103171668C206588197 @default.
- W3103171668 hasConceptScore W3103171668C38652104 @default.
- W3103171668 hasConceptScore W3103171668C41008148 @default.
- W3103171668 hasConceptScore W3103171668C41065033 @default.
- W3103171668 hasConceptScore W3103171668C548081761 @default.
- W3103171668 hasLocation W31031716681 @default.
- W3103171668 hasOpenAccess W3103171668 @default.
- W3103171668 hasPrimaryLocation W31031716681 @default.
- W3103171668 hasRelatedWork W1821941829 @default.
- W3103171668 hasRelatedWork W1853785581 @default.
- W3103171668 hasRelatedWork W2056584142 @default.
- W3103171668 hasRelatedWork W2254080459 @default.
- W3103171668 hasRelatedWork W2961085424 @default.
- W3103171668 hasRelatedWork W2978114883 @default.
- W3103171668 hasRelatedWork W4286629047 @default.
- W3103171668 hasRelatedWork W4306321456 @default.
- W3103171668 hasRelatedWork W4306674287 @default.
- W3103171668 hasRelatedWork W4224009465 @default.
- W3103171668 isParatext "false" @default.
- W3103171668 isRetracted "false" @default.
- W3103171668 magId "3103171668" @default.
- W3103171668 workType "article" @default.