Matches in SemOpenAlex for { <https://semopenalex.org/work/W2097828232> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W2097828232 endingPage "164" @default.
- W2097828232 startingPage "153" @default.
- W2097828232 abstract "Temporally extended actions (or macro-actions) have proven useful for speeding up planning and learning, adding robustness, and building prior knowledge into AI systems. The options framework, as introduced in Sutton, Precup and Singh (1999), provides a natural way to incorporate macro-actions into reinforcement learning. In the subgoals approach, learning is divided into two phases, first learning each option with a prescribed subgoal, and then learning to compose the learned options together. In this paper we offer a unified framework for concurrent inter- and intra-options learning. To that end, we propose a modular parameterization of intra-option policies together with option termination conditions and the option selection policy (inter options), and show that these three decision components may be viewed as a unified policy over an augmented state-action space, to which standard policy gradient algorithms may be applied. We identify the basis functions that apply to each of these decision components, and show that they possess a useful orthogonality property that allows to compute the natural gradient independently for each component. We further outline the extension of the suggested framework to several levels of options hierarchy, and conclude with a brief illustrative example." @default.
- W2097828232 created "2016-06-24" @default.
- W2097828232 creator A5007808379 @default.
- W2097828232 creator A5022424856 @default.
- W2097828232 date "2012-01-01" @default.
- W2097828232 modified "2023-09-25" @default.
- W2097828232 title "Unified Inter and Intra Options Learning Using Policy Gradient Methods" @default.
- W2097828232 cites W1507222174 @default.
- W2097828232 cites W1536990779 @default.
- W2097828232 cites W1968768508 @default.
- W2097828232 cites W1997318940 @default.
- W2097828232 cites W2017611213 @default.
- W2097828232 cites W2075245034 @default.
- W2097828232 cites W2094387729 @default.
- W2097828232 cites W2109910161 @default.
- W2097828232 cites W2132351269 @default.
- W2097828232 cites W2172968643 @default.
- W2097828232 doi "https://doi.org/10.1007/978-3-642-29946-9_17" @default.
- W2097828232 hasPublicationYear "2012" @default.
- W2097828232 type Work @default.
- W2097828232 sameAs 2097828232 @default.
- W2097828232 citedByCount "12" @default.
- W2097828232 countsByYear W20978282322014 @default.
- W2097828232 countsByYear W20978282322016 @default.
- W2097828232 countsByYear W20978282322017 @default.
- W2097828232 countsByYear W20978282322018 @default.
- W2097828232 countsByYear W20978282322019 @default.
- W2097828232 countsByYear W20978282322020 @default.
- W2097828232 countsByYear W20978282322022 @default.
- W2097828232 crossrefType "book-chapter" @default.
- W2097828232 hasAuthorship W2097828232A5007808379 @default.
- W2097828232 hasAuthorship W2097828232A5022424856 @default.
- W2097828232 hasBestOaLocation W20978282322 @default.
- W2097828232 hasConcept C154945302 @default.
- W2097828232 hasConcept C41008148 @default.
- W2097828232 hasConceptScore W2097828232C154945302 @default.
- W2097828232 hasConceptScore W2097828232C41008148 @default.
- W2097828232 hasLocation W20978282321 @default.
- W2097828232 hasLocation W20978282322 @default.
- W2097828232 hasOpenAccess W2097828232 @default.
- W2097828232 hasPrimaryLocation W20978282321 @default.
- W2097828232 hasRelatedWork W1596801655 @default.
- W2097828232 hasRelatedWork W2049775471 @default.
- W2097828232 hasRelatedWork W2350741829 @default.
- W2097828232 hasRelatedWork W2358668433 @default.
- W2097828232 hasRelatedWork W2376932109 @default.
- W2097828232 hasRelatedWork W2382290278 @default.
- W2097828232 hasRelatedWork W2390279801 @default.
- W2097828232 hasRelatedWork W2748952813 @default.
- W2097828232 hasRelatedWork W2899084033 @default.
- W2097828232 hasRelatedWork W2530322880 @default.
- W2097828232 isParatext "false" @default.
- W2097828232 isRetracted "false" @default.
- W2097828232 magId "2097828232" @default.
- W2097828232 workType "book-chapter" @default.