Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034808834> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3034808834 endingPage "5253" @default.
- W3034808834 startingPage "5243" @default.
- W3034808834 abstract "Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the features of their environment and the actions that are feasible. Gibson (1977) coined the term to describe the fact that certain states enable an agent to do certain actions, in the context of embodied agents. In this paper, we develop a theory of affordances for agents who learn and plan in Markov Decision Processes. Affordances play a dual role in this case. On one hand, they allow faster planning, by reducing the number of actions available in any given situation. On the other hand, they facilitate more efficient and precise learning of transition models from data, especially when such models require function approximation. We establish these properties through theoretical results as well as illustrative examples. We also propose an approach to learn affordances and use it to estimate transition models that are simpler and generalize better." @default.
- W3034808834 created "2020-06-19" @default.
- W3034808834 creator A5024581585 @default.
- W3034808834 creator A5028021826 @default.
- W3034808834 creator A5065836447 @default.
- W3034808834 creator A5080191195 @default.
- W3034808834 creator A5089433655 @default.
- W3034808834 date "2020-07-12" @default.
- W3034808834 modified "2023-09-23" @default.
- W3034808834 title "What can I do here? A Theory of Affordances in Reinforcement Learning" @default.
- W3034808834 hasPublicationYear "2020" @default.
- W3034808834 type Work @default.
- W3034808834 sameAs 3034808834 @default.
- W3034808834 citedByCount "11" @default.
- W3034808834 countsByYear W30348088342020 @default.
- W3034808834 countsByYear W30348088342021 @default.
- W3034808834 countsByYear W30348088342022 @default.
- W3034808834 crossrefType "proceedings-article" @default.
- W3034808834 hasAuthorship W3034808834A5024581585 @default.
- W3034808834 hasAuthorship W3034808834A5028021826 @default.
- W3034808834 hasAuthorship W3034808834A5065836447 @default.
- W3034808834 hasAuthorship W3034808834A5080191195 @default.
- W3034808834 hasAuthorship W3034808834A5089433655 @default.
- W3034808834 hasConcept C100609095 @default.
- W3034808834 hasConcept C105795698 @default.
- W3034808834 hasConcept C106189395 @default.
- W3034808834 hasConcept C107457646 @default.
- W3034808834 hasConcept C124952713 @default.
- W3034808834 hasConcept C14036430 @default.
- W3034808834 hasConcept C142362112 @default.
- W3034808834 hasConcept C151730666 @default.
- W3034808834 hasConcept C154945302 @default.
- W3034808834 hasConcept C159886148 @default.
- W3034808834 hasConcept C194995250 @default.
- W3034808834 hasConcept C2779343474 @default.
- W3034808834 hasConcept C2780980858 @default.
- W3034808834 hasConcept C33923547 @default.
- W3034808834 hasConcept C41008148 @default.
- W3034808834 hasConcept C78458016 @default.
- W3034808834 hasConcept C86803240 @default.
- W3034808834 hasConcept C97541855 @default.
- W3034808834 hasConceptScore W3034808834C100609095 @default.
- W3034808834 hasConceptScore W3034808834C105795698 @default.
- W3034808834 hasConceptScore W3034808834C106189395 @default.
- W3034808834 hasConceptScore W3034808834C107457646 @default.
- W3034808834 hasConceptScore W3034808834C124952713 @default.
- W3034808834 hasConceptScore W3034808834C14036430 @default.
- W3034808834 hasConceptScore W3034808834C142362112 @default.
- W3034808834 hasConceptScore W3034808834C151730666 @default.
- W3034808834 hasConceptScore W3034808834C154945302 @default.
- W3034808834 hasConceptScore W3034808834C159886148 @default.
- W3034808834 hasConceptScore W3034808834C194995250 @default.
- W3034808834 hasConceptScore W3034808834C2779343474 @default.
- W3034808834 hasConceptScore W3034808834C2780980858 @default.
- W3034808834 hasConceptScore W3034808834C33923547 @default.
- W3034808834 hasConceptScore W3034808834C41008148 @default.
- W3034808834 hasConceptScore W3034808834C78458016 @default.
- W3034808834 hasConceptScore W3034808834C86803240 @default.
- W3034808834 hasConceptScore W3034808834C97541855 @default.
- W3034808834 hasOpenAccess W3034808834 @default.
- W3034808834 hasRelatedWork W142783046 @default.
- W3034808834 hasRelatedWork W1579184372 @default.
- W3034808834 hasRelatedWork W1580568969 @default.
- W3034808834 hasRelatedWork W2078792342 @default.
- W3034808834 hasRelatedWork W2109910161 @default.
- W3034808834 hasRelatedWork W2121863487 @default.
- W3034808834 hasRelatedWork W2126738461 @default.
- W3034808834 hasRelatedWork W23830430 @default.
- W3034808834 hasRelatedWork W2559960928 @default.
- W3034808834 hasRelatedWork W2783497717 @default.
- W3034808834 hasRelatedWork W2885648612 @default.
- W3034808834 hasRelatedWork W2887627673 @default.
- W3034808834 hasRelatedWork W2890268033 @default.
- W3034808834 hasRelatedWork W2892364115 @default.
- W3034808834 hasRelatedWork W2892673593 @default.
- W3034808834 hasRelatedWork W2898504294 @default.
- W3034808834 hasRelatedWork W2967046678 @default.
- W3034808834 hasRelatedWork W3037991458 @default.
- W3034808834 hasRelatedWork W3079143028 @default.
- W3034808834 hasRelatedWork W567721252 @default.
- W3034808834 hasVolume "1" @default.
- W3034808834 isParatext "false" @default.
- W3034808834 isRetracted "false" @default.
- W3034808834 magId "3034808834" @default.
- W3034808834 workType "article" @default.