Matches in SemOpenAlex for { <https://semopenalex.org/work/W2804504503> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2804504503 abstract "The success or failure of any learning algorithm is partially due to the exploration strategy it exerts. However, most exploration strategies assume that the environment is star tionary and non-strategic. This work investigates how to design exploration strategies in non-stationary and adversarial environments. Our experimental setting uses a two agents strategic interaction scenario, where the opponent switches between different behavioral patterns. The agent's objective is to learn a model of the opponent's strategy to act optimally, despite non-determinism and stochasticity. Our contribution is twofold. First, we present drift exploration as a strategy for switch detection. Second, we propose a new algorithm called R-MAX# that reasons and acts in terms of two objectives: 1) to maximize utilities in the short term while learning and 2) eventually explore implicitly looking for opponent behavioral changes. We provide theoretical results showing that R-MAX# is guaranteed to detect the opponent's switch and learn a new model in terms of finite sample complexity." @default.
- W2804504503 created "2018-06-01" @default.
- W2804504503 creator A5001808269 @default.
- W2804504503 creator A5005259414 @default.
- W2804504503 creator A5044189592 @default.
- W2804504503 creator A5055612254 @default.
- W2804504503 creator A5064277708 @default.
- W2804504503 date "2017-05-08" @default.
- W2804504503 modified "2023-09-26" @default.
- W2804504503 title "An exploration strategy facing non-stationary agents (JAAMAS paper)" @default.
- W2804504503 hasPublicationYear "2017" @default.
- W2804504503 type Work @default.
- W2804504503 sameAs 2804504503 @default.
- W2804504503 citedByCount "0" @default.
- W2804504503 crossrefType "journal-article" @default.
- W2804504503 hasAuthorship W2804504503A5001808269 @default.
- W2804504503 hasAuthorship W2804504503A5005259414 @default.
- W2804504503 hasAuthorship W2804504503A5044189592 @default.
- W2804504503 hasAuthorship W2804504503A5055612254 @default.
- W2804504503 hasAuthorship W2804504503A5064277708 @default.
- W2804504503 hasConcept C121332964 @default.
- W2804504503 hasConcept C126255220 @default.
- W2804504503 hasConcept C145071142 @default.
- W2804504503 hasConcept C154945302 @default.
- W2804504503 hasConcept C33923547 @default.
- W2804504503 hasConcept C37736160 @default.
- W2804504503 hasConcept C38652104 @default.
- W2804504503 hasConcept C41008148 @default.
- W2804504503 hasConcept C41065033 @default.
- W2804504503 hasConcept C46814582 @default.
- W2804504503 hasConcept C61797465 @default.
- W2804504503 hasConcept C62520636 @default.
- W2804504503 hasConceptScore W2804504503C121332964 @default.
- W2804504503 hasConceptScore W2804504503C126255220 @default.
- W2804504503 hasConceptScore W2804504503C145071142 @default.
- W2804504503 hasConceptScore W2804504503C154945302 @default.
- W2804504503 hasConceptScore W2804504503C33923547 @default.
- W2804504503 hasConceptScore W2804504503C37736160 @default.
- W2804504503 hasConceptScore W2804504503C38652104 @default.
- W2804504503 hasConceptScore W2804504503C41008148 @default.
- W2804504503 hasConceptScore W2804504503C41065033 @default.
- W2804504503 hasConceptScore W2804504503C46814582 @default.
- W2804504503 hasConceptScore W2804504503C61797465 @default.
- W2804504503 hasConceptScore W2804504503C62520636 @default.
- W2804504503 hasLocation W28045045031 @default.
- W2804504503 hasOpenAccess W2804504503 @default.
- W2804504503 hasPrimaryLocation W28045045031 @default.
- W2804504503 hasRelatedWork W111799116 @default.
- W2804504503 hasRelatedWork W145813065 @default.
- W2804504503 hasRelatedWork W165982740 @default.
- W2804504503 hasRelatedWork W1974444340 @default.
- W2804504503 hasRelatedWork W1993194158 @default.
- W2804504503 hasRelatedWork W2135833051 @default.
- W2804504503 hasRelatedWork W2153866264 @default.
- W2804504503 hasRelatedWork W2158973351 @default.
- W2804504503 hasRelatedWork W2242236508 @default.
- W2804504503 hasRelatedWork W2266303891 @default.
- W2804504503 hasRelatedWork W2520213060 @default.
- W2804504503 hasRelatedWork W2531400694 @default.
- W2804504503 hasRelatedWork W2620929085 @default.
- W2804504503 hasRelatedWork W2889526206 @default.
- W2804504503 hasRelatedWork W3033616905 @default.
- W2804504503 hasRelatedWork W3037662176 @default.
- W2804504503 hasRelatedWork W3151813343 @default.
- W2804504503 hasRelatedWork W3153140474 @default.
- W2804504503 hasRelatedWork W3208893967 @default.
- W2804504503 hasRelatedWork W47267894 @default.
- W2804504503 isParatext "false" @default.
- W2804504503 isRetracted "false" @default.
- W2804504503 magId "2804504503" @default.
- W2804504503 workType "article" @default.