FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2973178003> ?p ?o ?g. }

• W2973178003 abstract "Option discovery and skill acquisition frameworks are integral to the functioning of a Hierarchically organized Reinforcement learning agent. However, such techniques often yield a large number of options or skills, which can potentially be represented succinctly by filtering out any redundant information. Such a reduction can reduce the required computation while also improving the performance on a target task. In order to compress an array of option policies, we attempt to find a policy basis that accurately captures the set of all options. In this work, we propose Option Encoder, an auto-encoder based framework with intelligently constrained weights, that helps discover a collection of basis policies. The policy basis can be used as a proxy for the original set of skills in a suitable hierarchically organized framework. We demonstrate the efficacy of our method on a collection of grid-worlds and on the high-dimensional Fetch-Reach robotic manipulation task by evaluating the obtained policy basis on a set of downstream tasks." @default.
• W2973178003 created "2019-09-19" @default.
• W2973178003 creator A5009374923 @default.
• W2973178003 creator A5033829963 @default.
• W2973178003 creator A5085453702 @default.
• W2973178003 date "2019-09-09" @default.
• W2973178003 modified "2023-09-27" @default.
• W2973178003 title "Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning" @default.
• W2973178003 cites W1536990779 @default.
• W2973178003 cites W1968768508 @default.
• W2973178003 cites W2090170171 @default.
• W2973178003 cites W2106008664 @default.
• W2973178003 cites W2106261932 @default.
• W2973178003 cites W2109910161 @default.
• W2973178003 cites W2119567691 @default.
• W2973178003 cites W2121863487 @default.
• W2973178003 cites W2143435603 @default.
• W2973178003 cites W2145339207 @default.
• W2973178003 cites W2155027007 @default.
• W2973178003 cites W2156737235 @default.
• W2973178003 cites W2161795906 @default.
• W2973178003 cites W2168640731 @default.
• W2973178003 cites W2173248099 @default.
• W2973178003 cites W2174786457 @default.
• W2973178003 cites W2215010794 @default.
• W2973178003 cites W2257979135 @default.
• W2973178003 cites W2312609093 @default.
• W2973178003 cites W2560647685 @default.
• W2973178003 cites W2583761661 @default.
• W2973178003 cites W2736601468 @default.
• W2973178003 cites W2789008106 @default.
• W2973178003 cites W2949267040 @default.
• W2973178003 cites W2949608212 @default.
• W2973178003 cites W2950040888 @default.
• W2973178003 cites W2963438456 @default.
• W2973178003 cites W2963946410 @default.
• W2973178003 cites W2964043796 @default.
• W2973178003 cites W2964227312 @default.
• W2973178003 cites W2971273232 @default.
• W2973178003 hasPublicationYear "2019" @default.
• W2973178003 type Work @default.
• W2973178003 sameAs 2973178003 @default.
• W2973178003 citedByCount "0" @default.
• W2973178003 crossrefType "posted-content" @default.
• W2973178003 hasAuthorship W2973178003A5009374923 @default.
• W2973178003 hasAuthorship W2973178003A5033829963 @default.
• W2973178003 hasAuthorship W2973178003A5085453702 @default.
• W2973178003 hasConcept C111919701 @default.
• W2973178003 hasConcept C11413529 @default.
• W2973178003 hasConcept C118505674 @default.
• W2973178003 hasConcept C119857082 @default.
• W2973178003 hasConcept C12426560 @default.
• W2973178003 hasConcept C127413603 @default.
• W2973178003 hasConcept C154945302 @default.
• W2973178003 hasConcept C177264268 @default.
• W2973178003 hasConcept C199360897 @default.
• W2973178003 hasConcept C201995342 @default.
• W2973178003 hasConcept C2524010 @default.
• W2973178003 hasConcept C2780451532 @default.
• W2973178003 hasConcept C33923547 @default.
• W2973178003 hasConcept C41008148 @default.
• W2973178003 hasConcept C45374587 @default.
• W2973178003 hasConcept C97541855 @default.
• W2973178003 hasConceptScore W2973178003C111919701 @default.
• W2973178003 hasConceptScore W2973178003C11413529 @default.
• W2973178003 hasConceptScore W2973178003C118505674 @default.
• W2973178003 hasConceptScore W2973178003C119857082 @default.
• W2973178003 hasConceptScore W2973178003C12426560 @default.
• W2973178003 hasConceptScore W2973178003C127413603 @default.
• W2973178003 hasConceptScore W2973178003C154945302 @default.
• W2973178003 hasConceptScore W2973178003C177264268 @default.
• W2973178003 hasConceptScore W2973178003C199360897 @default.
• W2973178003 hasConceptScore W2973178003C201995342 @default.
• W2973178003 hasConceptScore W2973178003C2524010 @default.
• W2973178003 hasConceptScore W2973178003C2780451532 @default.
• W2973178003 hasConceptScore W2973178003C33923547 @default.
• W2973178003 hasConceptScore W2973178003C41008148 @default.
• W2973178003 hasConceptScore W2973178003C45374587 @default.
• W2973178003 hasConceptScore W2973178003C97541855 @default.
• W2973178003 hasLocation W29731780031 @default.
• W2973178003 hasOpenAccess W2973178003 @default.
• W2973178003 hasPrimaryLocation W29731780031 @default.
• W2973178003 hasRelatedWork W1036107598 @default.
• W2973178003 hasRelatedWork W1549848204 @default.
• W2973178003 hasRelatedWork W1677904636 @default.
• W2973178003 hasRelatedWork W2064567069 @default.
• W2973178003 hasRelatedWork W2097828232 @default.
• W2973178003 hasRelatedWork W2106216543 @default.
• W2973178003 hasRelatedWork W2127288102 @default.
• W2973178003 hasRelatedWork W2169006000 @default.
• W2973178003 hasRelatedWork W2240922584 @default.
• W2973178003 hasRelatedWork W2570364481 @default.
• W2973178003 hasRelatedWork W2963912551 @default.
• W2973178003 hasRelatedWork W2965666670 @default.
• W2973178003 hasRelatedWork W2965762627 @default.
• W2973178003 hasRelatedWork W3080814299 @default.
• W2973178003 hasRelatedWork W3088052656 @default.
• W2973178003 hasRelatedWork W3092418144 @default.
• W2973178003 hasRelatedWork W3105525188 @default.
• W2973178003 hasRelatedWork W3134613326 @default.

• next