Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048851657> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3048851657 endingPage "148424" @default.
- W3048851657 startingPage "148411" @default.
- W3048851657 abstract "In this paper, we proposed a novel Hybrid Reinforcement Learning framework to maintain the stability of a biped robot (NAO) while it is walking on static and dynamic platforms. The reinforcement learning framework consists of the Model-based off-line Estimator, the Actor Network Pre-training scheme, and the Mode-free on-line optimizer. We proposed the Hierarchical Gaussian Processes as the Mode-based Estimator to predict a rough model of the system and to obtain the initial control input. Then, the initial control input is employed to pre-train the Actor Network by using the initial control input. Finally, a model-free optimizer based on Deep Deterministic Policy Gradient framework is introduced to fine tune the Actor Network and to generate the best actions. The proposed reinforcement learning framework not only successfully avoids the distribution mismatch problem while combining model-based scheme with model-free structure, but also improves the sample efficiency for the on-line learning procedure. Simulation results show that the proposed Hybrid Reinforcement Learning mechanism enables the NAO robot to maintain balance while walking on static and dynamic platforms. The robustness of the learned controllers in adapting to platforms with different angles, different magnitudes, and different frequencies is tested." @default.
- W3048851657 created "2020-08-18" @default.
- W3048851657 creator A5056248574 @default.
- W3048851657 creator A5078110256 @default.
- W3048851657 date "2020-01-01" @default.
- W3048851657 modified "2023-10-13" @default.
- W3048851657 title "Walking Control of a Biped Robot on Static and Rotating Platforms Based on Hybrid Reinforcement Learning" @default.
- W3048851657 cites W1989099984 @default.
- W3048851657 cites W2018705428 @default.
- W3048851657 cites W2035653862 @default.
- W3048851657 cites W2037729465 @default.
- W3048851657 cites W2050630772 @default.
- W3048851657 cites W2089476757 @default.
- W3048851657 cites W2107063340 @default.
- W3048851657 cites W2117031920 @default.
- W3048851657 cites W2129754669 @default.
- W3048851657 cites W2147828974 @default.
- W3048851657 cites W2278559600 @default.
- W3048851657 cites W2402164873 @default.
- W3048851657 cites W2568667779 @default.
- W3048851657 cites W2580909119 @default.
- W3048851657 cites W2791500836 @default.
- W3048851657 cites W2931363641 @default.
- W3048851657 cites W2962851396 @default.
- W3048851657 cites W2962872206 @default.
- W3048851657 cites W2964671970 @default.
- W3048851657 cites W2972798201 @default.
- W3048851657 doi "https://doi.org/10.1109/access.2020.3015506" @default.
- W3048851657 hasPublicationYear "2020" @default.
- W3048851657 type Work @default.
- W3048851657 sameAs 3048851657 @default.
- W3048851657 citedByCount "7" @default.
- W3048851657 countsByYear W30488516572022 @default.
- W3048851657 countsByYear W30488516572023 @default.
- W3048851657 crossrefType "journal-article" @default.
- W3048851657 hasAuthorship W3048851657A5056248574 @default.
- W3048851657 hasAuthorship W3048851657A5078110256 @default.
- W3048851657 hasBestOaLocation W30488516571 @default.
- W3048851657 hasConcept C127413603 @default.
- W3048851657 hasConcept C133731056 @default.
- W3048851657 hasConcept C154945302 @default.
- W3048851657 hasConcept C19966478 @default.
- W3048851657 hasConcept C2775924081 @default.
- W3048851657 hasConcept C41008148 @default.
- W3048851657 hasConcept C47446073 @default.
- W3048851657 hasConcept C65401140 @default.
- W3048851657 hasConcept C66938386 @default.
- W3048851657 hasConcept C67203356 @default.
- W3048851657 hasConcept C90509273 @default.
- W3048851657 hasConcept C97541855 @default.
- W3048851657 hasConceptScore W3048851657C127413603 @default.
- W3048851657 hasConceptScore W3048851657C133731056 @default.
- W3048851657 hasConceptScore W3048851657C154945302 @default.
- W3048851657 hasConceptScore W3048851657C19966478 @default.
- W3048851657 hasConceptScore W3048851657C2775924081 @default.
- W3048851657 hasConceptScore W3048851657C41008148 @default.
- W3048851657 hasConceptScore W3048851657C47446073 @default.
- W3048851657 hasConceptScore W3048851657C65401140 @default.
- W3048851657 hasConceptScore W3048851657C66938386 @default.
- W3048851657 hasConceptScore W3048851657C67203356 @default.
- W3048851657 hasConceptScore W3048851657C90509273 @default.
- W3048851657 hasConceptScore W3048851657C97541855 @default.
- W3048851657 hasFunder F4320334704 @default.
- W3048851657 hasLocation W30488516571 @default.
- W3048851657 hasOpenAccess W3048851657 @default.
- W3048851657 hasPrimaryLocation W30488516571 @default.
- W3048851657 hasRelatedWork W102060437 @default.
- W3048851657 hasRelatedWork W1534851618 @default.
- W3048851657 hasRelatedWork W1604883287 @default.
- W3048851657 hasRelatedWork W2055556366 @default.
- W3048851657 hasRelatedWork W2368249999 @default.
- W3048851657 hasRelatedWork W2907103250 @default.
- W3048851657 hasRelatedWork W3041867744 @default.
- W3048851657 hasRelatedWork W3080454990 @default.
- W3048851657 hasRelatedWork W3197674289 @default.
- W3048851657 hasRelatedWork W4282981148 @default.
- W3048851657 hasVolume "8" @default.
- W3048851657 isParatext "false" @default.
- W3048851657 isRetracted "false" @default.
- W3048851657 magId "3048851657" @default.
- W3048851657 workType "article" @default.