FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2523124567> ?p ?o ?g. }

• W2523124567 abstract "This paper introduces an automated skill acquisition framework in reinforcement learning which involves identifying a hierarchical description of the given task in terms of abstract states and extended actions between abstract states. Identifying such structures present in the task provides ways to simplify and speed up reinforcement learning algorithms. These structures also help to generalize such algorithms over multiple tasks without relearning policies from scratch. We use ideas from dynamical systems to find metastable regions in the state space and associate them with abstract states. The spectral clustering algorithm PCCA+ is used to identify suitable abstractions aligned to the underlying structure. Skills are defined in terms of the sequence of actions that lead to transitions between such abstract states. The connectivity information from PCCA+ is used to generate these skills or options. These skills are independent of the learning task and can be efficiently reused across a variety of tasks defined over the same model. This approach works well even without the exact model of the environment by using sample trajectories to construct an approximate estimate. We also present our approach to scaling the skill acquisition framework to complex tasks with large state spaces for which we perform state aggregation using the representation learned from an action conditional video prediction network and use the skill acquisition framework on the aggregated state space." @default.
• W2523124567 created "2016-09-30" @default.
• W2523124567 creator A5009374923 @default.
• W2523124567 creator A5013958846 @default.
• W2523124567 creator A5016085812 @default.
• W2523124567 creator A5026334494 @default.
• W2523124567 date "2016-05-17" @default.
• W2523124567 modified "2023-09-27" @default.
• W2523124567 title "Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering" @default.
• W2523124567 cites W1494114146 @default.
• W2523124567 cites W1515851193 @default.
• W2523124567 cites W1536990779 @default.
• W2523124567 cites W1545006598 @default.
• W2523124567 cites W1584307643 @default.
• W2523124567 cites W1595483645 @default.
• W2523124567 cites W200434350 @default.
• W2523124567 cites W2006533296 @default.
• W2523124567 cites W2109910161 @default.
• W2523124567 cites W2121517924 @default.
• W2523124567 cites W2121947440 @default.
• W2523124567 cites W2142838865 @default.
• W2523124567 cites W2143435603 @default.
• W2523124567 cites W2145339207 @default.
• W2523124567 cites W2165874743 @default.
• W2523124567 cites W2167945827 @default.
• W2523124567 cites W2168640731 @default.
• W2523124567 cites W2211996086 @default.
• W2523124567 cites W2260756217 @default.
• W2523124567 cites W2269570957 @default.
• W2523124567 cites W2335959470 @default.
• W2523124567 cites W2802774918 @default.
• W2523124567 cites W2962841471 @default.
• W2523124567 cites W2963477884 @default.
• W2523124567 cites W59183349 @default.
• W2523124567 hasPublicationYear "2016" @default.
• W2523124567 type Work @default.
• W2523124567 sameAs 2523124567 @default.
• W2523124567 citedByCount "16" @default.
• W2523124567 countsByYear W25231245672016 @default.
• W2523124567 countsByYear W25231245672017 @default.
• W2523124567 countsByYear W25231245672018 @default.
• W2523124567 countsByYear W25231245672019 @default.
• W2523124567 countsByYear W25231245672020 @default.
• W2523124567 countsByYear W25231245672021 @default.
• W2523124567 countsByYear W25231245672023 @default.
• W2523124567 crossrefType "posted-content" @default.
• W2523124567 hasAuthorship W2523124567A5009374923 @default.
• W2523124567 hasAuthorship W2523124567A5013958846 @default.
• W2523124567 hasAuthorship W2523124567A5016085812 @default.
• W2523124567 hasAuthorship W2523124567A5026334494 @default.
• W2523124567 hasConcept C105795698 @default.
• W2523124567 hasConcept C111919701 @default.
• W2523124567 hasConcept C119857082 @default.
• W2523124567 hasConcept C132758656 @default.
• W2523124567 hasConcept C136197465 @default.
• W2523124567 hasConcept C154945302 @default.
• W2523124567 hasConcept C162324750 @default.
• W2523124567 hasConcept C17744445 @default.
• W2523124567 hasConcept C187736073 @default.
• W2523124567 hasConcept C199360897 @default.
• W2523124567 hasConcept C199539241 @default.
• W2523124567 hasConcept C2776359362 @default.
• W2523124567 hasConcept C2778572836 @default.
• W2523124567 hasConcept C2780451532 @default.
• W2523124567 hasConcept C2780801425 @default.
• W2523124567 hasConcept C33923547 @default.
• W2523124567 hasConcept C41008148 @default.
• W2523124567 hasConcept C50522688 @default.
• W2523124567 hasConcept C72434380 @default.
• W2523124567 hasConcept C73555534 @default.
• W2523124567 hasConcept C94625758 @default.
• W2523124567 hasConcept C97541855 @default.
• W2523124567 hasConceptScore W2523124567C105795698 @default.
• W2523124567 hasConceptScore W2523124567C111919701 @default.
• W2523124567 hasConceptScore W2523124567C119857082 @default.
• W2523124567 hasConceptScore W2523124567C132758656 @default.
• W2523124567 hasConceptScore W2523124567C136197465 @default.
• W2523124567 hasConceptScore W2523124567C154945302 @default.
• W2523124567 hasConceptScore W2523124567C162324750 @default.
• W2523124567 hasConceptScore W2523124567C17744445 @default.
• W2523124567 hasConceptScore W2523124567C187736073 @default.
• W2523124567 hasConceptScore W2523124567C199360897 @default.
• W2523124567 hasConceptScore W2523124567C199539241 @default.
• W2523124567 hasConceptScore W2523124567C2776359362 @default.
• W2523124567 hasConceptScore W2523124567C2778572836 @default.
• W2523124567 hasConceptScore W2523124567C2780451532 @default.
• W2523124567 hasConceptScore W2523124567C2780801425 @default.
• W2523124567 hasConceptScore W2523124567C33923547 @default.
• W2523124567 hasConceptScore W2523124567C41008148 @default.
• W2523124567 hasConceptScore W2523124567C50522688 @default.
• W2523124567 hasConceptScore W2523124567C72434380 @default.
• W2523124567 hasConceptScore W2523124567C73555534 @default.
• W2523124567 hasConceptScore W2523124567C94625758 @default.
• W2523124567 hasConceptScore W2523124567C97541855 @default.
• W2523124567 hasLocation W25231245671 @default.
• W2523124567 hasOpenAccess W2523124567 @default.
• W2523124567 hasPrimaryLocation W25231245671 @default.
• W2523124567 hasRelatedWork W1492014007 @default.
• W2523124567 hasRelatedWork W1963873191 @default.
• W2523124567 hasRelatedWork W2108535023 @default.

• next