Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221008101> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4221008101 endingPage "108715" @default.
- W4221008101 startingPage "108715" @default.
- W4221008101 abstract "In Markov games, accurately detecting opponent policies and reusing optimal response policies is still a challenging problem. Most previous works assume that opponents switch their policies infrequently only at the end of an episode. However, the opponents may change their policies at high-frequency or even within an episode. Besides, the agent may achieve inconsistent optimal returns because of different opponent behaviors, which brings greater challenges to policy detection. This paper studies how to deal with the non-stationary opponent with abrupt policy changes through accurate policy detection and direct policy reuse. Specifically, we propose a context-aware Bayesian policy reuse (CABPR) algorithm to accurately identify and track the multi-strategic opponent. To continuously infer the opponent policy, an intra-episode belief is introduced taking advantage of opponent models. Within an episode, an inter-episode belief using Bayesian inference and the intra-episode belief are jointly used to detect the opponent type based on its behaviors and episodic rewards. Then the agent reuses the best response policies accordingly. We demonstrate the advantages of the proposed algorithm over several state-of-the-art algorithms in terms of episodic rewards, accumulated rewards, and detection accuracy in four competitive scenarios." @default.
- W4221008101 created "2022-04-03" @default.
- W4221008101 creator A5022499603 @default.
- W4221008101 creator A5072120380 @default.
- W4221008101 creator A5072963620 @default.
- W4221008101 creator A5083695433 @default.
- W4221008101 date "2022-05-01" @default.
- W4221008101 modified "2023-09-30" @default.
- W4221008101 title "Efficiently tracking multi-strategic opponents: A context-aware Bayesian policy reuse approach" @default.
- W4221008101 cites W1995875735 @default.
- W4221008101 cites W2008809493 @default.
- W4221008101 cites W2011418219 @default.
- W4221008101 cites W2022346311 @default.
- W4221008101 cites W2031727428 @default.
- W4221008101 cites W2103437045 @default.
- W4221008101 cites W2115524942 @default.
- W4221008101 cites W2134164581 @default.
- W4221008101 cites W2145339207 @default.
- W4221008101 cites W2158500619 @default.
- W4221008101 cites W2551398049 @default.
- W4221008101 cites W2617547828 @default.
- W4221008101 cites W2742108445 @default.
- W4221008101 cites W2760355785 @default.
- W4221008101 cites W2769567824 @default.
- W4221008101 cites W2921955147 @default.
- W4221008101 cites W2965433979 @default.
- W4221008101 cites W2997536466 @default.
- W4221008101 cites W3096650854 @default.
- W4221008101 cites W3112134271 @default.
- W4221008101 cites W32403112 @default.
- W4221008101 cites W778742492 @default.
- W4221008101 cites W952777547 @default.
- W4221008101 doi "https://doi.org/10.1016/j.asoc.2022.108715" @default.
- W4221008101 hasPublicationYear "2022" @default.
- W4221008101 type Work @default.
- W4221008101 citedByCount "1" @default.
- W4221008101 countsByYear W42210081012022 @default.
- W4221008101 crossrefType "journal-article" @default.
- W4221008101 hasAuthorship W4221008101A5022499603 @default.
- W4221008101 hasAuthorship W4221008101A5072120380 @default.
- W4221008101 hasAuthorship W4221008101A5072963620 @default.
- W4221008101 hasAuthorship W4221008101A5083695433 @default.
- W4221008101 hasConcept C105795698 @default.
- W4221008101 hasConcept C106189395 @default.
- W4221008101 hasConcept C107673813 @default.
- W4221008101 hasConcept C119857082 @default.
- W4221008101 hasConcept C151730666 @default.
- W4221008101 hasConcept C154945302 @default.
- W4221008101 hasConcept C159886148 @default.
- W4221008101 hasConcept C160234255 @default.
- W4221008101 hasConcept C18903297 @default.
- W4221008101 hasConcept C206588197 @default.
- W4221008101 hasConcept C2776214188 @default.
- W4221008101 hasConcept C2779343474 @default.
- W4221008101 hasConcept C33923547 @default.
- W4221008101 hasConcept C38652104 @default.
- W4221008101 hasConcept C41008148 @default.
- W4221008101 hasConcept C41065033 @default.
- W4221008101 hasConcept C82142266 @default.
- W4221008101 hasConcept C86803240 @default.
- W4221008101 hasConcept C98763669 @default.
- W4221008101 hasConceptScore W4221008101C105795698 @default.
- W4221008101 hasConceptScore W4221008101C106189395 @default.
- W4221008101 hasConceptScore W4221008101C107673813 @default.
- W4221008101 hasConceptScore W4221008101C119857082 @default.
- W4221008101 hasConceptScore W4221008101C151730666 @default.
- W4221008101 hasConceptScore W4221008101C154945302 @default.
- W4221008101 hasConceptScore W4221008101C159886148 @default.
- W4221008101 hasConceptScore W4221008101C160234255 @default.
- W4221008101 hasConceptScore W4221008101C18903297 @default.
- W4221008101 hasConceptScore W4221008101C206588197 @default.
- W4221008101 hasConceptScore W4221008101C2776214188 @default.
- W4221008101 hasConceptScore W4221008101C2779343474 @default.
- W4221008101 hasConceptScore W4221008101C33923547 @default.
- W4221008101 hasConceptScore W4221008101C38652104 @default.
- W4221008101 hasConceptScore W4221008101C41008148 @default.
- W4221008101 hasConceptScore W4221008101C41065033 @default.
- W4221008101 hasConceptScore W4221008101C82142266 @default.
- W4221008101 hasConceptScore W4221008101C86803240 @default.
- W4221008101 hasConceptScore W4221008101C98763669 @default.
- W4221008101 hasLocation W42210081011 @default.
- W4221008101 hasOpenAccess W4221008101 @default.
- W4221008101 hasPrimaryLocation W42210081011 @default.
- W4221008101 hasRelatedWork W2082830974 @default.
- W4221008101 hasRelatedWork W2114746372 @default.
- W4221008101 hasRelatedWork W2292692467 @default.
- W4221008101 hasRelatedWork W2511279186 @default.
- W4221008101 hasRelatedWork W2574982804 @default.
- W4221008101 hasRelatedWork W2753218748 @default.
- W4221008101 hasRelatedWork W2774409638 @default.
- W4221008101 hasRelatedWork W2963058055 @default.
- W4221008101 hasRelatedWork W3029748970 @default.
- W4221008101 hasRelatedWork W3210665603 @default.
- W4221008101 hasVolume "121" @default.
- W4221008101 isParatext "false" @default.
- W4221008101 isRetracted "false" @default.
- W4221008101 workType "article" @default.