Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206204219> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3206204219 abstract "Domain randomization (DR) is a powerful tool to make a policy robust to the uncertainty of dynamics caused by unobservable environmental parameters. Conventional DR has adopted model-free reinforcement learning as a policy optimizer. However, the model-free methods in DR demand high time-complexity due to the randomization process where the environment is extremely changed. In this paper, we introduce model-based dynamics and policy learning for efficient DR. A Bayesian model of locally linear embedding is designed to fit the stochastic dynamics in DR. By virtue of locally linear dynamics, model-based optimal control is substituted for the policy optimization. Unlike previous works, our proposed Bayesian model with a MNIW prior allows the locally linear embedding to capture the dynamics in DR as a stochastic model. We show that a training method that combines variational and adversarial approaches is adequate for Bayesian embedding. Finally, a model-based controller is designed on our Bayesian locally linear embedding, and it shows better performance in DR environments compared with the non-Bayesian model of locally linear embedding." @default.
- W3206204219 created "2021-10-25" @default.
- W3206204219 creator A5002367654 @default.
- W3206204219 creator A5032063647 @default.
- W3206204219 creator A5073996122 @default.
- W3206204219 date "2021-05-30" @default.
- W3206204219 modified "2023-09-25" @default.
- W3206204219 title "Model-based Domain Randomization of Dynamics System with Deep Bayesian Locally Linear Embedding" @default.
- W3206204219 cites W1959608418 @default.
- W3206204219 cites W2043286600 @default.
- W3206204219 cites W2087617385 @default.
- W3206204219 cites W2099471712 @default.
- W3206204219 cites W2212660284 @default.
- W3206204219 cites W2605102758 @default.
- W3206204219 cites W2736601468 @default.
- W3206204219 cites W2889347284 @default.
- W3206204219 cites W2895958971 @default.
- W3206204219 cites W2962957005 @default.
- W3206204219 cites W2963402509 @default.
- W3206204219 cites W2963430173 @default.
- W3206204219 cites W2963538198 @default.
- W3206204219 cites W2963630259 @default.
- W3206204219 cites W2963836885 @default.
- W3206204219 cites W2963919714 @default.
- W3206204219 cites W2964173023 @default.
- W3206204219 cites W2964214518 @default.
- W3206204219 cites W2966145721 @default.
- W3206204219 cites W3030141984 @default.
- W3206204219 cites W3037567775 @default.
- W3206204219 doi "https://doi.org/10.1109/icra48506.2021.9561942" @default.
- W3206204219 hasPublicationYear "2021" @default.
- W3206204219 type Work @default.
- W3206204219 sameAs 3206204219 @default.
- W3206204219 citedByCount "0" @default.
- W3206204219 crossrefType "proceedings-article" @default.
- W3206204219 hasAuthorship W3206204219A5002367654 @default.
- W3206204219 hasAuthorship W3206204219A5032063647 @default.
- W3206204219 hasAuthorship W3206204219A5073996122 @default.
- W3206204219 hasConcept C107673813 @default.
- W3206204219 hasConcept C11413529 @default.
- W3206204219 hasConcept C119857082 @default.
- W3206204219 hasConcept C126255220 @default.
- W3206204219 hasConcept C149782125 @default.
- W3206204219 hasConcept C154945302 @default.
- W3206204219 hasConcept C160234255 @default.
- W3206204219 hasConcept C163175372 @default.
- W3206204219 hasConcept C2780695315 @default.
- W3206204219 hasConcept C33923547 @default.
- W3206204219 hasConcept C41008148 @default.
- W3206204219 hasConcept C41608201 @default.
- W3206204219 hasConcept C97541855 @default.
- W3206204219 hasConceptScore W3206204219C107673813 @default.
- W3206204219 hasConceptScore W3206204219C11413529 @default.
- W3206204219 hasConceptScore W3206204219C119857082 @default.
- W3206204219 hasConceptScore W3206204219C126255220 @default.
- W3206204219 hasConceptScore W3206204219C149782125 @default.
- W3206204219 hasConceptScore W3206204219C154945302 @default.
- W3206204219 hasConceptScore W3206204219C160234255 @default.
- W3206204219 hasConceptScore W3206204219C163175372 @default.
- W3206204219 hasConceptScore W3206204219C2780695315 @default.
- W3206204219 hasConceptScore W3206204219C33923547 @default.
- W3206204219 hasConceptScore W3206204219C41008148 @default.
- W3206204219 hasConceptScore W3206204219C41608201 @default.
- W3206204219 hasConceptScore W3206204219C97541855 @default.
- W3206204219 hasFunder F4320323103 @default.
- W3206204219 hasLocation W32062042191 @default.
- W3206204219 hasOpenAccess W3206204219 @default.
- W3206204219 hasPrimaryLocation W32062042191 @default.
- W3206204219 hasRelatedWork W2110658950 @default.
- W3206204219 hasRelatedWork W2140035747 @default.
- W3206204219 hasRelatedWork W2511279186 @default.
- W3206204219 hasRelatedWork W2765250768 @default.
- W3206204219 hasRelatedWork W2901099257 @default.
- W3206204219 hasRelatedWork W2963058055 @default.
- W3206204219 hasRelatedWork W3022038857 @default.
- W3206204219 hasRelatedWork W3206204219 @default.
- W3206204219 hasRelatedWork W4206940412 @default.
- W3206204219 hasRelatedWork W4319083788 @default.
- W3206204219 isParatext "false" @default.
- W3206204219 isRetracted "false" @default.
- W3206204219 magId "3206204219" @default.
- W3206204219 workType "article" @default.