Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950462959> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2950462959 abstract "Reinforcement Learning algorithms can learn complex behavioral patterns for sequential decision making tasks wherein an agent interacts with an environment and acquires feedback in the form of rewards sampled from it. Traditionally, such algorithms make decisions, i.e., select actions to execute, at every single time step of the agent-environment interactions. In this paper, we propose a novel framework, Fine Grained Action Repetition (FiGAR), which enables the agent to decide the action as well as the time scale of repeating it. FiGAR can be used for improving any Deep Reinforcement Learning algorithm which maintains an explicit policy estimate by enabling temporal abstractions in the action space. We empirically demonstrate the efficacy of our framework by showing performance improvements on top of three policy search algorithms in different domains: Asynchronous Advantage Actor Critic in the Atari 2600 domain, Trust Region Policy Optimization in Mujoco domain and Deep Deterministic Policy Gradients in the TORCS car racing domain." @default.
- W2950462959 created "2019-06-27" @default.
- W2950462959 creator A5009374923 @default.
- W2950462959 creator A5021657850 @default.
- W2950462959 creator A5023986320 @default.
- W2950462959 date "2017-02-20" @default.
- W2950462959 modified "2023-09-27" @default.
- W2950462959 title "Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning" @default.
- W2950462959 cites W142462678 @default.
- W2950462959 cites W1515851193 @default.
- W2950462959 cites W1677182931 @default.
- W2950462959 cites W2121517924 @default.
- W2950462959 cites W2145339207 @default.
- W2950462959 cites W2153947321 @default.
- W2950462959 cites W2158782408 @default.
- W2950462959 cites W2163908189 @default.
- W2950462959 cites W2165150801 @default.
- W2950462959 cites W2173248099 @default.
- W2950462959 cites W2402219803 @default.
- W2950462959 cites W2428834750 @default.
- W2950462959 cites W2442341664 @default.
- W2950462959 cites W2529548870 @default.
- W2950462959 cites W2739657930 @default.
- W2950462959 cites W2919115771 @default.
- W2950462959 cites W2949608212 @default.
- W2950462959 cites W2963477884 @default.
- W2950462959 cites W2963830168 @default.
- W2950462959 cites W2964043796 @default.
- W2950462959 hasPublicationYear "2017" @default.
- W2950462959 type Work @default.
- W2950462959 sameAs 2950462959 @default.
- W2950462959 citedByCount "12" @default.
- W2950462959 countsByYear W29504629592018 @default.
- W2950462959 countsByYear W29504629592019 @default.
- W2950462959 countsByYear W29504629592020 @default.
- W2950462959 countsByYear W29504629592021 @default.
- W2950462959 crossrefType "posted-content" @default.
- W2950462959 hasAuthorship W2950462959A5009374923 @default.
- W2950462959 hasAuthorship W2950462959A5021657850 @default.
- W2950462959 hasAuthorship W2950462959A5023986320 @default.
- W2950462959 hasConcept C111919701 @default.
- W2950462959 hasConcept C119857082 @default.
- W2950462959 hasConcept C121332964 @default.
- W2950462959 hasConcept C134306372 @default.
- W2950462959 hasConcept C151319957 @default.
- W2950462959 hasConcept C154945302 @default.
- W2950462959 hasConcept C2778572836 @default.
- W2950462959 hasConcept C2780791683 @default.
- W2950462959 hasConcept C31258907 @default.
- W2950462959 hasConcept C33923547 @default.
- W2950462959 hasConcept C36503486 @default.
- W2950462959 hasConcept C41008148 @default.
- W2950462959 hasConcept C62520636 @default.
- W2950462959 hasConcept C97541855 @default.
- W2950462959 hasConceptScore W2950462959C111919701 @default.
- W2950462959 hasConceptScore W2950462959C119857082 @default.
- W2950462959 hasConceptScore W2950462959C121332964 @default.
- W2950462959 hasConceptScore W2950462959C134306372 @default.
- W2950462959 hasConceptScore W2950462959C151319957 @default.
- W2950462959 hasConceptScore W2950462959C154945302 @default.
- W2950462959 hasConceptScore W2950462959C2778572836 @default.
- W2950462959 hasConceptScore W2950462959C2780791683 @default.
- W2950462959 hasConceptScore W2950462959C31258907 @default.
- W2950462959 hasConceptScore W2950462959C33923547 @default.
- W2950462959 hasConceptScore W2950462959C36503486 @default.
- W2950462959 hasConceptScore W2950462959C41008148 @default.
- W2950462959 hasConceptScore W2950462959C62520636 @default.
- W2950462959 hasConceptScore W2950462959C97541855 @default.
- W2950462959 hasLocation W29504629591 @default.
- W2950462959 hasOpenAccess W2950462959 @default.
- W2950462959 hasPrimaryLocation W29504629591 @default.
- W2950462959 hasRelatedWork W1585861384 @default.
- W2950462959 hasRelatedWork W2109910161 @default.
- W2950462959 hasRelatedWork W2121863487 @default.
- W2950462959 hasRelatedWork W2145339207 @default.
- W2950462959 hasRelatedWork W2158150115 @default.
- W2950462959 hasRelatedWork W2173248099 @default.
- W2950462959 hasRelatedWork W2605102581 @default.
- W2950462959 hasRelatedWork W2670080482 @default.
- W2950462959 hasRelatedWork W2789102901 @default.
- W2950462959 hasRelatedWork W2789410350 @default.
- W2950462959 hasRelatedWork W2897697565 @default.
- W2950462959 hasRelatedWork W2946824041 @default.
- W2950462959 hasRelatedWork W2950038834 @default.
- W2950462959 hasRelatedWork W2950197980 @default.
- W2950462959 hasRelatedWork W2952348496 @default.
- W2950462959 hasRelatedWork W2963262099 @default.
- W2950462959 hasRelatedWork W2963934593 @default.
- W2950462959 hasRelatedWork W2964043796 @default.
- W2950462959 hasRelatedWork W298069310 @default.
- W2950462959 hasRelatedWork W76760840 @default.
- W2950462959 isParatext "false" @default.
- W2950462959 isRetracted "false" @default.
- W2950462959 magId "2950462959" @default.
- W2950462959 workType "article" @default.