Matches in SemOpenAlex for { <https://semopenalex.org/work/W4302010614> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4302010614 abstract "In continuous control, exploration is often performed through undirected strategies in which parameters of the networks or selected actions are perturbed by random noise. Although the deep setting of undirected exploration has been shown to improve the performance of on-policy methods, they introduce an excessive computational complexity and are known to fail in the off-policy setting. The intrinsically motivated exploration is an effective alternative to the undirected strategies, but they are usually studied for discrete action domains. In this paper, we investigate how intrinsic motivation can effectively be combined with deep reinforcement learning in the control of continuous systems to obtain a directed exploratory behavior. We adapt the existing theories on animal motivational systems into the reinforcement learning paradigm and introduce a novel and scalable directed exploration strategy. The introduced approach, motivated by the maximization of the value function's error, can benefit from a collected set of experiences by extracting useful information and unify the intrinsic exploration motivations in the literature under a single exploration objective. An extensive set of empirical studies demonstrate that our framework extends to larger and more diverse state spaces, dramatically improves the baselines, and outperforms the undirected strategies significantly." @default.
- W4302010614 created "2022-10-06" @default.
- W4302010614 creator A5040880684 @default.
- W4302010614 creator A5089040739 @default.
- W4302010614 date "2022-10-01" @default.
- W4302010614 modified "2023-10-18" @default.
- W4302010614 title "Deep Intrinsically Motivated Exploration in Continuous Control" @default.
- W4302010614 doi "https://doi.org/10.48550/arxiv.2210.00293" @default.
- W4302010614 hasPublicationYear "2022" @default.
- W4302010614 type Work @default.
- W4302010614 citedByCount "0" @default.
- W4302010614 crossrefType "posted-content" @default.
- W4302010614 hasAuthorship W4302010614A5040880684 @default.
- W4302010614 hasAuthorship W4302010614A5089040739 @default.
- W4302010614 hasBestOaLocation W43020106141 @default.
- W4302010614 hasConcept C119857082 @default.
- W4302010614 hasConcept C121332964 @default.
- W4302010614 hasConcept C126255220 @default.
- W4302010614 hasConcept C14036430 @default.
- W4302010614 hasConcept C154945302 @default.
- W4302010614 hasConcept C177264268 @default.
- W4302010614 hasConcept C199360897 @default.
- W4302010614 hasConcept C2775924081 @default.
- W4302010614 hasConcept C2776330181 @default.
- W4302010614 hasConcept C2780791683 @default.
- W4302010614 hasConcept C33923547 @default.
- W4302010614 hasConcept C41008148 @default.
- W4302010614 hasConcept C48044578 @default.
- W4302010614 hasConcept C62520636 @default.
- W4302010614 hasConcept C77088390 @default.
- W4302010614 hasConcept C78458016 @default.
- W4302010614 hasConcept C86803240 @default.
- W4302010614 hasConcept C97541855 @default.
- W4302010614 hasConceptScore W4302010614C119857082 @default.
- W4302010614 hasConceptScore W4302010614C121332964 @default.
- W4302010614 hasConceptScore W4302010614C126255220 @default.
- W4302010614 hasConceptScore W4302010614C14036430 @default.
- W4302010614 hasConceptScore W4302010614C154945302 @default.
- W4302010614 hasConceptScore W4302010614C177264268 @default.
- W4302010614 hasConceptScore W4302010614C199360897 @default.
- W4302010614 hasConceptScore W4302010614C2775924081 @default.
- W4302010614 hasConceptScore W4302010614C2776330181 @default.
- W4302010614 hasConceptScore W4302010614C2780791683 @default.
- W4302010614 hasConceptScore W4302010614C33923547 @default.
- W4302010614 hasConceptScore W4302010614C41008148 @default.
- W4302010614 hasConceptScore W4302010614C48044578 @default.
- W4302010614 hasConceptScore W4302010614C62520636 @default.
- W4302010614 hasConceptScore W4302010614C77088390 @default.
- W4302010614 hasConceptScore W4302010614C78458016 @default.
- W4302010614 hasConceptScore W4302010614C86803240 @default.
- W4302010614 hasConceptScore W4302010614C97541855 @default.
- W4302010614 hasLocation W43020106141 @default.
- W4302010614 hasOpenAccess W4302010614 @default.
- W4302010614 hasPrimaryLocation W43020106141 @default.
- W4302010614 hasRelatedWork W2154611954 @default.
- W4302010614 hasRelatedWork W2352513997 @default.
- W4302010614 hasRelatedWork W2371811322 @default.
- W4302010614 hasRelatedWork W2962686687 @default.
- W4302010614 hasRelatedWork W3014586007 @default.
- W4302010614 hasRelatedWork W3022038857 @default.
- W4302010614 hasRelatedWork W3170446423 @default.
- W4302010614 hasRelatedWork W3213373898 @default.
- W4302010614 hasRelatedWork W4210735998 @default.
- W4302010614 hasRelatedWork W4319083788 @default.
- W4302010614 isParatext "false" @default.
- W4302010614 isRetracted "false" @default.
- W4302010614 workType "article" @default.