Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285338583> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4285338583 abstract "Traditional meta reinforcement learning based on task inference separates task inference with task control, but ignores the importance of exploration during task inference. The agent uses the same policy for both task exploration process and task control process, which leads to low task inference efficiency. To solve this problem, this paper proposes a task inference based meta reinforcement learning framework (Separating Explorer from Task Inference based Meta-Reinforcement Learning, SETIMRL). In this framework, an explorer agent is specially designed for task inference. The explorer takes the task exploration fully, and transits the collected data to the inference network. And the actor will adapt to the new tasks rapidly with the received inference information, which helps improve the model’s performance. Experimental results show that the proposed algorithm has better efficiency in multi-dimensions and sequential control tasks, compared to traditional meta reinforcement learning based on task inference." @default.
- W4285338583 created "2022-07-14" @default.
- W4285338583 creator A5002343968 @default.
- W4285338583 creator A5012325495 @default.
- W4285338583 creator A5029045415 @default.
- W4285338583 creator A5033684035 @default.
- W4285338583 creator A5063732891 @default.
- W4285338583 date "2021-11-01" @default.
- W4285338583 modified "2023-10-16" @default.
- W4285338583 title "Separating Explorer for Task Inference Based Meta Reinforcement Learning Algorithm" @default.
- W4285338583 doi "https://doi.org/10.1109/insai54028.2021.00048" @default.
- W4285338583 hasPublicationYear "2021" @default.
- W4285338583 type Work @default.
- W4285338583 citedByCount "0" @default.
- W4285338583 crossrefType "proceedings-article" @default.
- W4285338583 hasAuthorship W4285338583A5002343968 @default.
- W4285338583 hasAuthorship W4285338583A5012325495 @default.
- W4285338583 hasAuthorship W4285338583A5029045415 @default.
- W4285338583 hasAuthorship W4285338583A5033684035 @default.
- W4285338583 hasAuthorship W4285338583A5063732891 @default.
- W4285338583 hasConcept C111919701 @default.
- W4285338583 hasConcept C119857082 @default.
- W4285338583 hasConcept C127413603 @default.
- W4285338583 hasConcept C154945302 @default.
- W4285338583 hasConcept C175154964 @default.
- W4285338583 hasConcept C201995342 @default.
- W4285338583 hasConcept C2775924081 @default.
- W4285338583 hasConcept C2776214188 @default.
- W4285338583 hasConcept C2780451532 @default.
- W4285338583 hasConcept C2781002164 @default.
- W4285338583 hasConcept C41008148 @default.
- W4285338583 hasConcept C97541855 @default.
- W4285338583 hasConcept C98045186 @default.
- W4285338583 hasConceptScore W4285338583C111919701 @default.
- W4285338583 hasConceptScore W4285338583C119857082 @default.
- W4285338583 hasConceptScore W4285338583C127413603 @default.
- W4285338583 hasConceptScore W4285338583C154945302 @default.
- W4285338583 hasConceptScore W4285338583C175154964 @default.
- W4285338583 hasConceptScore W4285338583C201995342 @default.
- W4285338583 hasConceptScore W4285338583C2775924081 @default.
- W4285338583 hasConceptScore W4285338583C2776214188 @default.
- W4285338583 hasConceptScore W4285338583C2780451532 @default.
- W4285338583 hasConceptScore W4285338583C2781002164 @default.
- W4285338583 hasConceptScore W4285338583C41008148 @default.
- W4285338583 hasConceptScore W4285338583C97541855 @default.
- W4285338583 hasConceptScore W4285338583C98045186 @default.
- W4285338583 hasFunder F4320321001 @default.
- W4285338583 hasLocation W42853385831 @default.
- W4285338583 hasOpenAccess W4285338583 @default.
- W4285338583 hasPrimaryLocation W42853385831 @default.
- W4285338583 hasRelatedWork W3022038857 @default.
- W4285338583 hasRelatedWork W3090436287 @default.
- W4285338583 hasRelatedWork W3092824172 @default.
- W4285338583 hasRelatedWork W3105036711 @default.
- W4285338583 hasRelatedWork W3200361725 @default.
- W4285338583 hasRelatedWork W3212190400 @default.
- W4285338583 hasRelatedWork W4226082087 @default.
- W4285338583 hasRelatedWork W4287647350 @default.
- W4285338583 hasRelatedWork W4319083788 @default.
- W4285338583 hasRelatedWork W4319309271 @default.
- W4285338583 isParatext "false" @default.
- W4285338583 isRetracted "false" @default.
- W4285338583 workType "article" @default.