Matches in SemOpenAlex for { <https://semopenalex.org/work/W144573208> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W144573208 abstract "The application of reinforcement learning algorithms to Partially Observable Stochastic Games (POSG) is challenging since each agent does not have access to the whole state information and, in case of concurrent learners, the environment has non-stationary dynamics. These problems could be partially overcome if the policies followed by the other agents were known, and, for this reason, many approaches try to estimate them through the so-called opponent modeling techniques. Although many researches have been devoted to the study of the accuracy of the estimation of opponents’ policies, still little attention has been deserved to understand in which situations these model estimations can be actually useful to improve the agent’s performance. This paper presents a preliminary study about the impact of using opponent modeling techniques to learn the solution of a POSG. Our main purpose is to provide a measure of the gain in performance that can be obtained by exploiting information about the policy of other agents, and how this gain is affected by the accuracy of the estimated models. Our analysis focus on a small two-agent POSG: the Kuhn Poker, a simplified version of classical poker. Three cases will be considered according to the agent knowledge about the opponent’s policy: no knowledge, perfect knowledge, and imperfect knowledge. The aim is to identify which is the maximum error that can affect the model estimate without leading to a performance lower than that reachable without using opponent-modeling information. Finally, we will show how the results of this analysis can be used to improve the performance of a reinforcement-learning algorithm coped with a simple opponent modeling technique." @default.
- W144573208 created "2016-06-24" @default.
- W144573208 creator A5014791481 @default.
- W144573208 creator A5017130830 @default.
- W144573208 creator A5059695931 @default.
- W144573208 date "2008-01-01" @default.
- W144573208 modified "2023-09-23" @default.
- W144573208 title "On the Usefulness of Opponent Modeling: the Kuhn Poker case study (Short Paper)" @default.
- W144573208 cites W2083347533 @default.
- W144573208 cites W2101861158 @default.
- W144573208 cites W2121863487 @default.
- W144573208 cites W2146628995 @default.
- W144573208 cites W3089351328 @default.
- W144573208 hasPublicationYear "2008" @default.
- W144573208 type Work @default.
- W144573208 sameAs 144573208 @default.
- W144573208 citedByCount "0" @default.
- W144573208 crossrefType "journal-article" @default.
- W144573208 hasAuthorship W144573208A5014791481 @default.
- W144573208 hasAuthorship W144573208A5017130830 @default.
- W144573208 hasAuthorship W144573208A5059695931 @default.
- W144573208 hasConcept C113336015 @default.
- W144573208 hasConcept C119857082 @default.
- W144573208 hasConcept C120665830 @default.
- W144573208 hasConcept C121332964 @default.
- W144573208 hasConcept C123676819 @default.
- W144573208 hasConcept C138885662 @default.
- W144573208 hasConcept C144237770 @default.
- W144573208 hasConcept C154945302 @default.
- W144573208 hasConcept C192209626 @default.
- W144573208 hasConcept C2780310539 @default.
- W144573208 hasConcept C33923547 @default.
- W144573208 hasConcept C38652104 @default.
- W144573208 hasConcept C41008148 @default.
- W144573208 hasConcept C41065033 @default.
- W144573208 hasConcept C41895202 @default.
- W144573208 hasConcept C97541855 @default.
- W144573208 hasConceptScore W144573208C113336015 @default.
- W144573208 hasConceptScore W144573208C119857082 @default.
- W144573208 hasConceptScore W144573208C120665830 @default.
- W144573208 hasConceptScore W144573208C121332964 @default.
- W144573208 hasConceptScore W144573208C123676819 @default.
- W144573208 hasConceptScore W144573208C138885662 @default.
- W144573208 hasConceptScore W144573208C144237770 @default.
- W144573208 hasConceptScore W144573208C154945302 @default.
- W144573208 hasConceptScore W144573208C192209626 @default.
- W144573208 hasConceptScore W144573208C2780310539 @default.
- W144573208 hasConceptScore W144573208C33923547 @default.
- W144573208 hasConceptScore W144573208C38652104 @default.
- W144573208 hasConceptScore W144573208C41008148 @default.
- W144573208 hasConceptScore W144573208C41065033 @default.
- W144573208 hasConceptScore W144573208C41895202 @default.
- W144573208 hasConceptScore W144573208C97541855 @default.
- W144573208 hasOpenAccess W144573208 @default.
- W144573208 hasRelatedWork W1562872111 @default.
- W144573208 hasRelatedWork W1576354143 @default.
- W144573208 hasRelatedWork W1595285848 @default.
- W144573208 hasRelatedWork W201931040 @default.
- W144573208 hasRelatedWork W2026829590 @default.
- W144573208 hasRelatedWork W2137980100 @default.
- W144573208 hasRelatedWork W2140443131 @default.
- W144573208 hasRelatedWork W2142273982 @default.
- W144573208 hasRelatedWork W2284238120 @default.
- W144573208 hasRelatedWork W2419083025 @default.
- W144573208 hasRelatedWork W2769567824 @default.
- W144573208 hasRelatedWork W2911623172 @default.
- W144573208 hasRelatedWork W2963639492 @default.
- W144573208 hasRelatedWork W3007925142 @default.
- W144573208 hasRelatedWork W3041742050 @default.
- W144573208 hasRelatedWork W3083310462 @default.
- W144573208 hasRelatedWork W3100469848 @default.
- W144573208 hasRelatedWork W97179957 @default.
- W144573208 hasRelatedWork W144670910 @default.
- W144573208 hasRelatedWork W2559431516 @default.
- W144573208 isParatext "false" @default.
- W144573208 isRetracted "false" @default.
- W144573208 magId "144573208" @default.
- W144573208 workType "article" @default.