Matches in SemOpenAlex for { <https://semopenalex.org/work/W2126173398> ?p ?o ?g. }
Showing items 1 to 51 of
51
with 100 items per page.
- W2126173398 abstract "In the this paper, a CMAC-Q-learning based Dyna agent is presented to relieve the problem of learning speed in reinforcement learning, in order to achieve the goals of shortening training process and increasing the learning, speed. We combine CMAC, Q-learning, and prioritized sweeping techniques to construct the Dyna agent in which a Q-learning is trained for policy learning; meanwhile, model approximators, called CMAC-model and CMAC-R-model, are in charge of approximating the environment model. The approximated model provides the Q-learning with virtual interaction experience to further update the policy within the time gap when there is no interplay between the agent and the real environment. The Dyna agent switches seamlessly between the real environment and the virtual environment model for the objective of policy learning. A simulation for controlling a differential-drive mobile robot has been conducted to demonstrate that the proposed method can preliminarily achieve the design goal." @default.
- W2126173398 created "2016-06-24" @default.
- W2126173398 creator A5001081733 @default.
- W2126173398 creator A5026272279 @default.
- W2126173398 creator A5046113161 @default.
- W2126173398 date "2008-08-01" @default.
- W2126173398 modified "2023-10-05" @default.
- W2126173398 title "A CMAC-Q-Learning based Dyna agent" @default.
- W2126173398 cites W1557517019 @default.
- W2126173398 cites W1980035368 @default.
- W2126173398 cites W1993740947 @default.
- W2126173398 cites W2048226872 @default.
- W2126173398 cites W2121863487 @default.
- W2126173398 cites W32403112 @default.
- W2126173398 doi "https://doi.org/10.1109/sice.2008.4655167" @default.
- W2126173398 hasPublicationYear "2008" @default.
- W2126173398 type Work @default.
- W2126173398 sameAs 2126173398 @default.
- W2126173398 citedByCount "4" @default.
- W2126173398 countsByYear W21261733982012 @default.
- W2126173398 countsByYear W21261733982017 @default.
- W2126173398 countsByYear W21261733982021 @default.
- W2126173398 crossrefType "proceedings-article" @default.
- W2126173398 hasAuthorship W2126173398A5001081733 @default.
- W2126173398 hasAuthorship W2126173398A5026272279 @default.
- W2126173398 hasAuthorship W2126173398A5046113161 @default.
- W2126173398 hasConcept C154945302 @default.
- W2126173398 hasConcept C188116033 @default.
- W2126173398 hasConcept C41008148 @default.
- W2126173398 hasConcept C97541855 @default.
- W2126173398 hasConceptScore W2126173398C154945302 @default.
- W2126173398 hasConceptScore W2126173398C188116033 @default.
- W2126173398 hasConceptScore W2126173398C41008148 @default.
- W2126173398 hasConceptScore W2126173398C97541855 @default.
- W2126173398 hasLocation W21261733981 @default.
- W2126173398 hasOpenAccess W2126173398 @default.
- W2126173398 hasPrimaryLocation W21261733981 @default.
- W2126173398 hasRelatedWork W2130043461 @default.
- W2126173398 hasRelatedWork W2350741829 @default.
- W2126173398 hasRelatedWork W2358668433 @default.
- W2126173398 hasRelatedWork W2376932109 @default.
- W2126173398 hasRelatedWork W2382290278 @default.
- W2126173398 hasRelatedWork W2390279801 @default.
- W2126173398 hasRelatedWork W2748952813 @default.
- W2126173398 hasRelatedWork W2899084033 @default.
- W2126173398 hasRelatedWork W3179674455 @default.
- W2126173398 hasRelatedWork W4206669594 @default.
- W2126173398 isParatext "false" @default.
- W2126173398 isRetracted "false" @default.
- W2126173398 magId "2126173398" @default.
- W2126173398 workType "article" @default.