Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287330329> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4287330329 abstract "Model-based reinforcement learning (MBRL) approaches rely on discrete-time state transition models whereas physical systems and the vast majority of control tasks operate in continuous-time. To avoid time-discretization approximation of the underlying process, we propose a continuous-time MBRL framework based on a novel actor-critic method. Our approach also infers the unknown state evolution differentials with Bayesian neural ordinary differential equations (ODE) to account for epistemic uncertainty. We implement and test our method on a new ODE-RL suite that explicitly solves continuous-time control systems. Our experiments illustrate that the model is robust against irregular and noisy data, is sample-efficient, and can solve control problems which pose challenges to discrete-time MBRL methods." @default.
- W4287330329 created "2022-07-25" @default.
- W4287330329 creator A5007032257 @default.
- W4287330329 creator A5043112498 @default.
- W4287330329 creator A5049442192 @default.
- W4287330329 date "2021-02-09" @default.
- W4287330329 modified "2023-09-27" @default.
- W4287330329 title "Continuous-Time Model-Based Reinforcement Learning" @default.
- W4287330329 doi "https://doi.org/10.48550/arxiv.2102.04764" @default.
- W4287330329 hasPublicationYear "2021" @default.
- W4287330329 type Work @default.
- W4287330329 citedByCount "0" @default.
- W4287330329 crossrefType "posted-content" @default.
- W4287330329 hasAuthorship W4287330329A5007032257 @default.
- W4287330329 hasAuthorship W4287330329A5043112498 @default.
- W4287330329 hasAuthorship W4287330329A5049442192 @default.
- W4287330329 hasBestOaLocation W42873303291 @default.
- W4287330329 hasConcept C105795698 @default.
- W4287330329 hasConcept C111919701 @default.
- W4287330329 hasConcept C11413529 @default.
- W4287330329 hasConcept C119857082 @default.
- W4287330329 hasConcept C134306372 @default.
- W4287330329 hasConcept C154945302 @default.
- W4287330329 hasConcept C28826006 @default.
- W4287330329 hasConcept C33923547 @default.
- W4287330329 hasConcept C34862557 @default.
- W4287330329 hasConcept C41008148 @default.
- W4287330329 hasConcept C48103436 @default.
- W4287330329 hasConcept C51544822 @default.
- W4287330329 hasConcept C55689738 @default.
- W4287330329 hasConcept C73000952 @default.
- W4287330329 hasConcept C78045399 @default.
- W4287330329 hasConcept C97541855 @default.
- W4287330329 hasConcept C98045186 @default.
- W4287330329 hasConceptScore W4287330329C105795698 @default.
- W4287330329 hasConceptScore W4287330329C111919701 @default.
- W4287330329 hasConceptScore W4287330329C11413529 @default.
- W4287330329 hasConceptScore W4287330329C119857082 @default.
- W4287330329 hasConceptScore W4287330329C134306372 @default.
- W4287330329 hasConceptScore W4287330329C154945302 @default.
- W4287330329 hasConceptScore W4287330329C28826006 @default.
- W4287330329 hasConceptScore W4287330329C33923547 @default.
- W4287330329 hasConceptScore W4287330329C34862557 @default.
- W4287330329 hasConceptScore W4287330329C41008148 @default.
- W4287330329 hasConceptScore W4287330329C48103436 @default.
- W4287330329 hasConceptScore W4287330329C51544822 @default.
- W4287330329 hasConceptScore W4287330329C55689738 @default.
- W4287330329 hasConceptScore W4287330329C73000952 @default.
- W4287330329 hasConceptScore W4287330329C78045399 @default.
- W4287330329 hasConceptScore W4287330329C97541855 @default.
- W4287330329 hasConceptScore W4287330329C98045186 @default.
- W4287330329 hasLocation W42873303291 @default.
- W4287330329 hasLocation W42873303292 @default.
- W4287330329 hasOpenAccess W4287330329 @default.
- W4287330329 hasPrimaryLocation W42873303291 @default.
- W4287330329 hasRelatedWork W1734480611 @default.
- W4287330329 hasRelatedWork W2769297273 @default.
- W4287330329 hasRelatedWork W2947757285 @default.
- W4287330329 hasRelatedWork W2974753373 @default.
- W4287330329 hasRelatedWork W2985965953 @default.
- W4287330329 hasRelatedWork W3010795166 @default.
- W4287330329 hasRelatedWork W3022038857 @default.
- W4287330329 hasRelatedWork W4210299439 @default.
- W4287330329 hasRelatedWork W4280495772 @default.
- W4287330329 hasRelatedWork W4319083788 @default.
- W4287330329 isParatext "false" @default.
- W4287330329 isRetracted "false" @default.
- W4287330329 workType "article" @default.