Matches in SemOpenAlex for { <https://semopenalex.org/work/W4365420630> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4365420630 endingPage "417" @default.
- W4365420630 startingPage "406" @default.
- W4365420630 abstract "Generalizability is a formidable challenge in applying reinforcement learning to the real world. The root cause of poor generalization performance in reinforcement learning is that generalization from a limited number of training conditions to unseen test conditions results in implicit partial observability, effectively transforming even fully observed Markov Decision Process (MDP) into Partially Observable Markov Decision Process (POMDP). To address such issues, we propose a novel structure, namely Context-adapted Multi-policy Ensemble Method (CAMPE), which enables the model to adapt to changes in the environment and efficiently solve implicit partial observability during generalization. The method captures local dynamic changes by learning contextual environment latent variables to equip the model with the ability of environment adaption. The latent variables and samples with contextual information are used as the input of the policy. Multiple policies are trained, combined in an integrated way to obtain a single policy to approximately solve the problem of partial observability. We demonstrate our method on various simulated robotics and control tasks. Experimental results show that our method achieves superior generalization ability." @default.
- W4365420630 created "2023-04-14" @default.
- W4365420630 creator A5030271803 @default.
- W4365420630 creator A5044809241 @default.
- W4365420630 creator A5069584904 @default.
- W4365420630 date "2023-01-01" @default.
- W4365420630 modified "2023-09-28" @default.
- W4365420630 title "Context-Adapted Multi-policy Ensemble Method for Generalization in Reinforcement Learning" @default.
- W4365420630 cites W1564670092 @default.
- W4365420630 cites W2034725503 @default.
- W4365420630 cites W2087992130 @default.
- W4365420630 cites W2110962519 @default.
- W4365420630 cites W2116753650 @default.
- W4365420630 cites W2158782408 @default.
- W4365420630 cites W2570651606 @default.
- W4365420630 cites W2605102758 @default.
- W4365420630 cites W2792005857 @default.
- W4365420630 cites W2949736877 @default.
- W4365420630 cites W3103780890 @default.
- W4365420630 doi "https://doi.org/10.1007/978-3-031-30105-6_34" @default.
- W4365420630 hasPublicationYear "2023" @default.
- W4365420630 type Work @default.
- W4365420630 citedByCount "0" @default.
- W4365420630 crossrefType "book-chapter" @default.
- W4365420630 hasAuthorship W4365420630A5030271803 @default.
- W4365420630 hasAuthorship W4365420630A5044809241 @default.
- W4365420630 hasAuthorship W4365420630A5069584904 @default.
- W4365420630 hasConcept C105795698 @default.
- W4365420630 hasConcept C106189395 @default.
- W4365420630 hasConcept C111919701 @default.
- W4365420630 hasConcept C119857082 @default.
- W4365420630 hasConcept C134306372 @default.
- W4365420630 hasConcept C151730666 @default.
- W4365420630 hasConcept C154945302 @default.
- W4365420630 hasConcept C159886148 @default.
- W4365420630 hasConcept C163836022 @default.
- W4365420630 hasConcept C17098449 @default.
- W4365420630 hasConcept C177148314 @default.
- W4365420630 hasConcept C27158222 @default.
- W4365420630 hasConcept C2779343474 @default.
- W4365420630 hasConcept C28826006 @default.
- W4365420630 hasConcept C33923547 @default.
- W4365420630 hasConcept C36299963 @default.
- W4365420630 hasConcept C41008148 @default.
- W4365420630 hasConcept C45942800 @default.
- W4365420630 hasConcept C51167844 @default.
- W4365420630 hasConcept C86803240 @default.
- W4365420630 hasConcept C97541855 @default.
- W4365420630 hasConcept C98045186 @default.
- W4365420630 hasConcept C98763669 @default.
- W4365420630 hasConceptScore W4365420630C105795698 @default.
- W4365420630 hasConceptScore W4365420630C106189395 @default.
- W4365420630 hasConceptScore W4365420630C111919701 @default.
- W4365420630 hasConceptScore W4365420630C119857082 @default.
- W4365420630 hasConceptScore W4365420630C134306372 @default.
- W4365420630 hasConceptScore W4365420630C151730666 @default.
- W4365420630 hasConceptScore W4365420630C154945302 @default.
- W4365420630 hasConceptScore W4365420630C159886148 @default.
- W4365420630 hasConceptScore W4365420630C163836022 @default.
- W4365420630 hasConceptScore W4365420630C17098449 @default.
- W4365420630 hasConceptScore W4365420630C177148314 @default.
- W4365420630 hasConceptScore W4365420630C27158222 @default.
- W4365420630 hasConceptScore W4365420630C2779343474 @default.
- W4365420630 hasConceptScore W4365420630C28826006 @default.
- W4365420630 hasConceptScore W4365420630C33923547 @default.
- W4365420630 hasConceptScore W4365420630C36299963 @default.
- W4365420630 hasConceptScore W4365420630C41008148 @default.
- W4365420630 hasConceptScore W4365420630C45942800 @default.
- W4365420630 hasConceptScore W4365420630C51167844 @default.
- W4365420630 hasConceptScore W4365420630C86803240 @default.
- W4365420630 hasConceptScore W4365420630C97541855 @default.
- W4365420630 hasConceptScore W4365420630C98045186 @default.
- W4365420630 hasConceptScore W4365420630C98763669 @default.
- W4365420630 hasLocation W43654206301 @default.
- W4365420630 hasOpenAccess W4365420630 @default.
- W4365420630 hasPrimaryLocation W43654206301 @default.
- W4365420630 hasRelatedWork W1932117986 @default.
- W4365420630 hasRelatedWork W1966071689 @default.
- W4365420630 hasRelatedWork W199494732 @default.
- W4365420630 hasRelatedWork W2024405129 @default.
- W4365420630 hasRelatedWork W2149126181 @default.
- W4365420630 hasRelatedWork W2156371714 @default.
- W4365420630 hasRelatedWork W3128073777 @default.
- W4365420630 hasRelatedWork W3167472281 @default.
- W4365420630 hasRelatedWork W3211465897 @default.
- W4365420630 hasRelatedWork W4285429136 @default.
- W4365420630 isParatext "false" @default.
- W4365420630 isRetracted "false" @default.
- W4365420630 workType "book-chapter" @default.