Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765397130> ?p ?o ?g. }
- W2765397130 abstract "In order for robots to perform mission-critical tasks, it is essential that they are able to quickly adapt to changes in their environment as well as to injuries and or other bodily changes. Deep reinforcement learning has been shown to be successful in training robot control policies for operation in complex environments. However, existing methods typically employ only a single policy. This can limit the adaptability since a large environmental modification might require a completely different behavior compared to the learning environment. To solve this problem, we propose Map-based Multi-Policy Reinforcement Learning (MMPRL), which aims to search and store multiple policies that encode different behavioral features while maximizing the expected reward in advance of the environment change. Thanks to these policies, which are stored into a multi-dimensional discrete map according to its behavioral feature, adaptation can be performed within reasonable time without retraining the robot. An appropriate pre-trained policy from the map can be recalled using Bayesian optimization. Our experiments show that MMPRL enables robots to quickly adapt to large changes without requiring any prior knowledge on the type of injuries that could occur. A highlight of the learned behaviors can be found here: this https URL ." @default.
- W2765397130 created "2017-11-10" @default.
- W2765397130 creator A5005792703 @default.
- W2765397130 creator A5010520720 @default.
- W2765397130 creator A5016566504 @default.
- W2765397130 creator A5074598961 @default.
- W2765397130 creator A5085499213 @default.
- W2765397130 date "2017-10-17" @default.
- W2765397130 modified "2023-09-27" @default.
- W2765397130 title "Map-based Multi-Policy Reinforcement Learning: Enhancing Adaptability of Robots by Deep Reinforcement Learning." @default.
- W2765397130 cites W1738827650 @default.
- W2765397130 cites W1757796397 @default.
- W2765397130 cites W1979328769 @default.
- W2765397130 cites W2111178261 @default.
- W2765397130 cites W2138784882 @default.
- W2765397130 cites W2145339207 @default.
- W2765397130 cites W2158782408 @default.
- W2765397130 cites W2173248099 @default.
- W2765397130 cites W2291973609 @default.
- W2765397130 cites W2410983263 @default.
- W2765397130 cites W2529477964 @default.
- W2765397130 cites W2553303224 @default.
- W2765397130 cites W2580175322 @default.
- W2765397130 cites W2586431331 @default.
- W2765397130 cites W2593744649 @default.
- W2765397130 cites W2596367596 @default.
- W2765397130 cites W2606327391 @default.
- W2765397130 cites W2735796404 @default.
- W2765397130 cites W2737821837 @default.
- W2765397130 cites W2738778707 @default.
- W2765397130 cites W2747402019 @default.
- W2765397130 cites W2949267040 @default.
- W2765397130 cites W2949608212 @default.
- W2765397130 cites W2952606116 @default.
- W2765397130 cites W2952765942 @default.
- W2765397130 cites W2963684914 @default.
- W2765397130 cites W2964043796 @default.
- W2765397130 cites W2964121744 @default.
- W2765397130 cites W2964161785 @default.
- W2765397130 hasPublicationYear "2017" @default.
- W2765397130 type Work @default.
- W2765397130 sameAs 2765397130 @default.
- W2765397130 citedByCount "2" @default.
- W2765397130 countsByYear W27653971302019 @default.
- W2765397130 countsByYear W27653971302021 @default.
- W2765397130 crossrefType "posted-content" @default.
- W2765397130 hasAuthorship W2765397130A5005792703 @default.
- W2765397130 hasAuthorship W2765397130A5010520720 @default.
- W2765397130 hasAuthorship W2765397130A5016566504 @default.
- W2765397130 hasAuthorship W2765397130A5074598961 @default.
- W2765397130 hasAuthorship W2765397130A5085499213 @default.
- W2765397130 hasConcept C104317684 @default.
- W2765397130 hasConcept C107457646 @default.
- W2765397130 hasConcept C119857082 @default.
- W2765397130 hasConcept C120665830 @default.
- W2765397130 hasConcept C121332964 @default.
- W2765397130 hasConcept C127413603 @default.
- W2765397130 hasConcept C138885662 @default.
- W2765397130 hasConcept C139807058 @default.
- W2765397130 hasConcept C144133560 @default.
- W2765397130 hasConcept C154945302 @default.
- W2765397130 hasConcept C155202549 @default.
- W2765397130 hasConcept C177606310 @default.
- W2765397130 hasConcept C185592680 @default.
- W2765397130 hasConcept C188888258 @default.
- W2765397130 hasConcept C18903297 @default.
- W2765397130 hasConcept C19966478 @default.
- W2765397130 hasConcept C2776401178 @default.
- W2765397130 hasConcept C2778712577 @default.
- W2765397130 hasConcept C41008148 @default.
- W2765397130 hasConcept C41895202 @default.
- W2765397130 hasConcept C55493867 @default.
- W2765397130 hasConcept C66746571 @default.
- W2765397130 hasConcept C66938386 @default.
- W2765397130 hasConcept C67203356 @default.
- W2765397130 hasConcept C86803240 @default.
- W2765397130 hasConcept C90509273 @default.
- W2765397130 hasConcept C97541855 @default.
- W2765397130 hasConceptScore W2765397130C104317684 @default.
- W2765397130 hasConceptScore W2765397130C107457646 @default.
- W2765397130 hasConceptScore W2765397130C119857082 @default.
- W2765397130 hasConceptScore W2765397130C120665830 @default.
- W2765397130 hasConceptScore W2765397130C121332964 @default.
- W2765397130 hasConceptScore W2765397130C127413603 @default.
- W2765397130 hasConceptScore W2765397130C138885662 @default.
- W2765397130 hasConceptScore W2765397130C139807058 @default.
- W2765397130 hasConceptScore W2765397130C144133560 @default.
- W2765397130 hasConceptScore W2765397130C154945302 @default.
- W2765397130 hasConceptScore W2765397130C155202549 @default.
- W2765397130 hasConceptScore W2765397130C177606310 @default.
- W2765397130 hasConceptScore W2765397130C185592680 @default.
- W2765397130 hasConceptScore W2765397130C188888258 @default.
- W2765397130 hasConceptScore W2765397130C18903297 @default.
- W2765397130 hasConceptScore W2765397130C19966478 @default.
- W2765397130 hasConceptScore W2765397130C2776401178 @default.
- W2765397130 hasConceptScore W2765397130C2778712577 @default.
- W2765397130 hasConceptScore W2765397130C41008148 @default.
- W2765397130 hasConceptScore W2765397130C41895202 @default.
- W2765397130 hasConceptScore W2765397130C55493867 @default.
- W2765397130 hasConceptScore W2765397130C66746571 @default.