Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288725462> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4288725462 abstract "Learning in high dimensional continuous tasks is challenging, mainly when the experience replay memory is very limited. We introduce a simple yet effective experience sharing mechanism for deterministic policies in continuous action domains for the future off-policy deep reinforcement learning applications in which the allocated memory for the experience replay buffer is limited. To overcome the extrapolation error induced by learning from other agents' experiences, we facilitate our algorithm with a novel off-policy correction technique without any action probability estimates. We test the effectiveness of our method in challenging OpenAI Gym continuous control tasks and conclude that it can achieve a safe experience sharing across multiple agents and exhibits a robust performance when the replay memory is strictly limited." @default.
- W4288725462 created "2022-07-30" @default.
- W4288725462 creator A5040880684 @default.
- W4288725462 creator A5049034491 @default.
- W4288725462 creator A5070280309 @default.
- W4288725462 creator A5089040739 @default.
- W4288725462 date "2022-07-27" @default.
- W4288725462 modified "2023-10-18" @default.
- W4288725462 title "Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms" @default.
- W4288725462 doi "https://doi.org/10.48550/arxiv.2207.13453" @default.
- W4288725462 hasPublicationYear "2022" @default.
- W4288725462 type Work @default.
- W4288725462 citedByCount "0" @default.
- W4288725462 crossrefType "posted-content" @default.
- W4288725462 hasAuthorship W4288725462A5040880684 @default.
- W4288725462 hasAuthorship W4288725462A5049034491 @default.
- W4288725462 hasAuthorship W4288725462A5070280309 @default.
- W4288725462 hasAuthorship W4288725462A5089040739 @default.
- W4288725462 hasBestOaLocation W42887254621 @default.
- W4288725462 hasConcept C111472728 @default.
- W4288725462 hasConcept C11413529 @default.
- W4288725462 hasConcept C119857082 @default.
- W4288725462 hasConcept C121332964 @default.
- W4288725462 hasConcept C132459708 @default.
- W4288725462 hasConcept C134306372 @default.
- W4288725462 hasConcept C138885662 @default.
- W4288725462 hasConcept C154945302 @default.
- W4288725462 hasConcept C2775924081 @default.
- W4288725462 hasConcept C2780586882 @default.
- W4288725462 hasConcept C2780791683 @default.
- W4288725462 hasConcept C33923547 @default.
- W4288725462 hasConcept C41008148 @default.
- W4288725462 hasConcept C62520636 @default.
- W4288725462 hasConcept C97541855 @default.
- W4288725462 hasConceptScore W4288725462C111472728 @default.
- W4288725462 hasConceptScore W4288725462C11413529 @default.
- W4288725462 hasConceptScore W4288725462C119857082 @default.
- W4288725462 hasConceptScore W4288725462C121332964 @default.
- W4288725462 hasConceptScore W4288725462C132459708 @default.
- W4288725462 hasConceptScore W4288725462C134306372 @default.
- W4288725462 hasConceptScore W4288725462C138885662 @default.
- W4288725462 hasConceptScore W4288725462C154945302 @default.
- W4288725462 hasConceptScore W4288725462C2775924081 @default.
- W4288725462 hasConceptScore W4288725462C2780586882 @default.
- W4288725462 hasConceptScore W4288725462C2780791683 @default.
- W4288725462 hasConceptScore W4288725462C33923547 @default.
- W4288725462 hasConceptScore W4288725462C41008148 @default.
- W4288725462 hasConceptScore W4288725462C62520636 @default.
- W4288725462 hasConceptScore W4288725462C97541855 @default.
- W4288725462 hasLocation W42887254621 @default.
- W4288725462 hasOpenAccess W4288725462 @default.
- W4288725462 hasPrimaryLocation W42887254621 @default.
- W4288725462 hasRelatedWork W102453 @default.
- W4288725462 hasRelatedWork W11104910 @default.
- W4288725462 hasRelatedWork W12428677 @default.
- W4288725462 hasRelatedWork W1323832 @default.
- W4288725462 hasRelatedWork W2683128 @default.
- W4288725462 hasRelatedWork W3471107 @default.
- W4288725462 hasRelatedWork W361876 @default.
- W4288725462 hasRelatedWork W3942861 @default.
- W4288725462 hasRelatedWork W5081013 @default.
- W4288725462 hasRelatedWork W5991403 @default.
- W4288725462 isParatext "false" @default.
- W4288725462 isRetracted "false" @default.
- W4288725462 workType "article" @default.