Matches in SemOpenAlex for { <https://semopenalex.org/work/W567721252> ?p ?o ?g. }
- W567721252 endingPage "1320" @default.
- W567721252 startingPage "1312" @default.
- W567721252 abstract "Value functions are a core component of reinforcement learning systems. The main idea is to to construct a single function approximator V (s; θ) that estimates the long-term reward from any state s, using parameters θ. In this paper we introduce universal value function approximators (UVFAs) V (s, g; θ) that generalise not just over states s but also over goals g. We develop an efficient technique for supervised learning of UVFAs, by factoring observed values into separate embedding vectors for state and goal, and then learning a mapping from s and g to these factored embedding vectors. We show how this technique may be incorporated into a reinforcement learning algorithm that updates the UVFA solely from observed rewards. Finally, we demonstrate that a UVFA can successfully generalise to previously unseen goals." @default.
- W567721252 created "2016-06-24" @default.
- W567721252 creator A5022506974 @default.
- W567721252 creator A5042475428 @default.
- W567721252 creator A5081322018 @default.
- W567721252 creator A5091771290 @default.
- W567721252 date "2015-07-06" @default.
- W567721252 modified "2023-10-02" @default.
- W567721252 title "Universal Value Function Approximators" @default.
- W567721252 cites W1507087299 @default.
- W567721252 cites W1515851193 @default.
- W567721252 cites W1598748993 @default.
- W567721252 cites W1600046456 @default.
- W567721252 cites W1757796397 @default.
- W567721252 cites W1969074599 @default.
- W567721252 cites W2047191624 @default.
- W567721252 cites W2097498341 @default.
- W567721252 cites W2109910161 @default.
- W567721252 cites W2123542217 @default.
- W567721252 cites W2132622533 @default.
- W567721252 cites W2133853511 @default.
- W567721252 cites W2153579005 @default.
- W567721252 cites W2158899491 @default.
- W567721252 cites W2159752377 @default.
- W567721252 cites W2159849946 @default.
- W567721252 cites W2169300227 @default.
- W567721252 cites W2187089797 @default.
- W567721252 cites W2203345135 @default.
- W567721252 cites W2913340405 @default.
- W567721252 cites W2949834189 @default.
- W567721252 cites W2964121744 @default.
- W567721252 cites W753012316 @default.
- W567721252 hasPublicationYear "2015" @default.
- W567721252 type Work @default.
- W567721252 sameAs 567721252 @default.
- W567721252 citedByCount "431" @default.
- W567721252 countsByYear W5677212522015 @default.
- W567721252 countsByYear W5677212522016 @default.
- W567721252 countsByYear W5677212522017 @default.
- W567721252 countsByYear W5677212522018 @default.
- W567721252 countsByYear W5677212522019 @default.
- W567721252 countsByYear W5677212522020 @default.
- W567721252 countsByYear W5677212522021 @default.
- W567721252 countsByYear W5677212522022 @default.
- W567721252 countsByYear W5677212522023 @default.
- W567721252 crossrefType "proceedings-article" @default.
- W567721252 hasAuthorship W567721252A5022506974 @default.
- W567721252 hasAuthorship W567721252A5042475428 @default.
- W567721252 hasAuthorship W567721252A5081322018 @default.
- W567721252 hasAuthorship W567721252A5091771290 @default.
- W567721252 hasConcept C10138342 @default.
- W567721252 hasConcept C11413529 @default.
- W567721252 hasConcept C119857082 @default.
- W567721252 hasConcept C121332964 @default.
- W567721252 hasConcept C126255220 @default.
- W567721252 hasConcept C14036430 @default.
- W567721252 hasConcept C14646407 @default.
- W567721252 hasConcept C154945302 @default.
- W567721252 hasConcept C162324750 @default.
- W567721252 hasConcept C168167062 @default.
- W567721252 hasConcept C177225278 @default.
- W567721252 hasConcept C199360897 @default.
- W567721252 hasConcept C2164484 @default.
- W567721252 hasConcept C2776291640 @default.
- W567721252 hasConcept C2780801425 @default.
- W567721252 hasConcept C33923547 @default.
- W567721252 hasConcept C41008148 @default.
- W567721252 hasConcept C41608201 @default.
- W567721252 hasConcept C48103436 @default.
- W567721252 hasConcept C61797465 @default.
- W567721252 hasConcept C62520636 @default.
- W567721252 hasConcept C76155785 @default.
- W567721252 hasConcept C78458016 @default.
- W567721252 hasConcept C86803240 @default.
- W567721252 hasConcept C97355855 @default.
- W567721252 hasConcept C97541855 @default.
- W567721252 hasConceptScore W567721252C10138342 @default.
- W567721252 hasConceptScore W567721252C11413529 @default.
- W567721252 hasConceptScore W567721252C119857082 @default.
- W567721252 hasConceptScore W567721252C121332964 @default.
- W567721252 hasConceptScore W567721252C126255220 @default.
- W567721252 hasConceptScore W567721252C14036430 @default.
- W567721252 hasConceptScore W567721252C14646407 @default.
- W567721252 hasConceptScore W567721252C154945302 @default.
- W567721252 hasConceptScore W567721252C162324750 @default.
- W567721252 hasConceptScore W567721252C168167062 @default.
- W567721252 hasConceptScore W567721252C177225278 @default.
- W567721252 hasConceptScore W567721252C199360897 @default.
- W567721252 hasConceptScore W567721252C2164484 @default.
- W567721252 hasConceptScore W567721252C2776291640 @default.
- W567721252 hasConceptScore W567721252C2780801425 @default.
- W567721252 hasConceptScore W567721252C33923547 @default.
- W567721252 hasConceptScore W567721252C41008148 @default.
- W567721252 hasConceptScore W567721252C41608201 @default.
- W567721252 hasConceptScore W567721252C48103436 @default.
- W567721252 hasConceptScore W567721252C61797465 @default.
- W567721252 hasConceptScore W567721252C62520636 @default.
- W567721252 hasConceptScore W567721252C76155785 @default.