Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313886525> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4313886525 abstract "In this paper, we propose ensemble inverse model network based disturbance observer (EIMN-DOB) to improve the robustness of the policy network (PN) which is a training result of policy based reinforcement learning (RL), without physical modeling. EIMN-DOB uses the ensemble model of the inverse model network (IMN), which acts as a nominal inverse model, and can estimate and cancel model uncertainty and disturbance like a typical disturbance observer (DOB) without a physical modeling. Because EIMN is trained from the data used in training RL, the additional training data for expressing the inverse model are not required. The experiments in this paper appeared that the PN of soft actor critic(SAC) combined with EIMN-DOB maintains control performance even in the presence of disturbance in continuous control benchmark tasks based on Mujoco physics engine. When the trained PN is used with EIMN-DOB in the real environment, the control performance in simulator can be preserved in the real environment, and it is expected to be utilized to minimize the sim-to-real gap of RL." @default.
- W4313886525 created "2023-01-10" @default.
- W4313886525 creator A5013003378 @default.
- W4313886525 creator A5020732596 @default.
- W4313886525 creator A5069368669 @default.
- W4313886525 date "2022-11-27" @default.
- W4313886525 modified "2023-10-18" @default.
- W4313886525 title "How to easily make a policy network of reinforcement learning robust without physical modeling" @default.
- W4313886525 cites W2230652337 @default.
- W4313886525 cites W2343986152 @default.
- W4313886525 cites W2605102758 @default.
- W4313886525 cites W3010680978 @default.
- W4313886525 cites W3011575162 @default.
- W4313886525 cites W3086019649 @default.
- W4313886525 cites W3207110310 @default.
- W4313886525 doi "https://doi.org/10.23919/iccas55662.2022.10003696" @default.
- W4313886525 hasPublicationYear "2022" @default.
- W4313886525 type Work @default.
- W4313886525 citedByCount "0" @default.
- W4313886525 crossrefType "proceedings-article" @default.
- W4313886525 hasAuthorship W4313886525A5013003378 @default.
- W4313886525 hasAuthorship W4313886525A5020732596 @default.
- W4313886525 hasAuthorship W4313886525A5069368669 @default.
- W4313886525 hasConcept C104317684 @default.
- W4313886525 hasConcept C119599485 @default.
- W4313886525 hasConcept C127413603 @default.
- W4313886525 hasConcept C13280743 @default.
- W4313886525 hasConcept C133731056 @default.
- W4313886525 hasConcept C151730666 @default.
- W4313886525 hasConcept C154945302 @default.
- W4313886525 hasConcept C17500928 @default.
- W4313886525 hasConcept C185592680 @default.
- W4313886525 hasConcept C185798385 @default.
- W4313886525 hasConcept C205649164 @default.
- W4313886525 hasConcept C207467116 @default.
- W4313886525 hasConcept C2524010 @default.
- W4313886525 hasConcept C2775924081 @default.
- W4313886525 hasConcept C2777601987 @default.
- W4313886525 hasConcept C31531917 @default.
- W4313886525 hasConcept C33923547 @default.
- W4313886525 hasConcept C41008148 @default.
- W4313886525 hasConcept C44154836 @default.
- W4313886525 hasConcept C47446073 @default.
- W4313886525 hasConcept C55493867 @default.
- W4313886525 hasConcept C63479239 @default.
- W4313886525 hasConcept C86803240 @default.
- W4313886525 hasConcept C97541855 @default.
- W4313886525 hasConceptScore W4313886525C104317684 @default.
- W4313886525 hasConceptScore W4313886525C119599485 @default.
- W4313886525 hasConceptScore W4313886525C127413603 @default.
- W4313886525 hasConceptScore W4313886525C13280743 @default.
- W4313886525 hasConceptScore W4313886525C133731056 @default.
- W4313886525 hasConceptScore W4313886525C151730666 @default.
- W4313886525 hasConceptScore W4313886525C154945302 @default.
- W4313886525 hasConceptScore W4313886525C17500928 @default.
- W4313886525 hasConceptScore W4313886525C185592680 @default.
- W4313886525 hasConceptScore W4313886525C185798385 @default.
- W4313886525 hasConceptScore W4313886525C205649164 @default.
- W4313886525 hasConceptScore W4313886525C207467116 @default.
- W4313886525 hasConceptScore W4313886525C2524010 @default.
- W4313886525 hasConceptScore W4313886525C2775924081 @default.
- W4313886525 hasConceptScore W4313886525C2777601987 @default.
- W4313886525 hasConceptScore W4313886525C31531917 @default.
- W4313886525 hasConceptScore W4313886525C33923547 @default.
- W4313886525 hasConceptScore W4313886525C41008148 @default.
- W4313886525 hasConceptScore W4313886525C44154836 @default.
- W4313886525 hasConceptScore W4313886525C47446073 @default.
- W4313886525 hasConceptScore W4313886525C55493867 @default.
- W4313886525 hasConceptScore W4313886525C63479239 @default.
- W4313886525 hasConceptScore W4313886525C86803240 @default.
- W4313886525 hasConceptScore W4313886525C97541855 @default.
- W4313886525 hasLocation W43138865251 @default.
- W4313886525 hasOpenAccess W4313886525 @default.
- W4313886525 hasPrimaryLocation W43138865251 @default.
- W4313886525 hasRelatedWork W1486578725 @default.
- W4313886525 hasRelatedWork W1925787989 @default.
- W4313886525 hasRelatedWork W2028053381 @default.
- W4313886525 hasRelatedWork W2029885876 @default.
- W4313886525 hasRelatedWork W2066749370 @default.
- W4313886525 hasRelatedWork W2067224748 @default.
- W4313886525 hasRelatedWork W2123546991 @default.
- W4313886525 hasRelatedWork W2288178599 @default.
- W4313886525 hasRelatedWork W2351202984 @default.
- W4313886525 hasRelatedWork W4250295346 @default.
- W4313886525 isParatext "false" @default.
- W4313886525 isRetracted "false" @default.
- W4313886525 workType "article" @default.