Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385966000> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4385966000 abstract "Stochastic optimal control with unknown randomness distributions has been studied for a long time, encompassing robust control, distributionally robust control, and adaptive control. We propose a new episodic Bayesian approach that incorporates Bayesian learning with optimal control. In each episode, the approach learns the randomness distribution with a Bayesian posterior and subsequently solves the corresponding Bayesian average estimate of the true problem. The resulting policy is exercised during the episode, while additional data/observations of the randomness are collected to update the Bayesian posterior for the next episode. We show that the resulting episodic value functions and policies converge almost surely to their optimal counterparts of the true problem if the parametrized model of the randomness distribution is correctly specified. We further show that the asymptotic convergence rate of the episodic value functions is of the order $O(N^{-1/2})$. We develop an efficient computational method based on stochastic dual dynamic programming for a class of problems that have convex value functions. Our numerical results on a classical inventory control problem verify the theoretical convergence results and demonstrate the effectiveness of the proposed computational method." @default.
- W4385966000 created "2023-08-18" @default.
- W4385966000 creator A5025917676 @default.
- W4385966000 creator A5032561481 @default.
- W4385966000 creator A5068512850 @default.
- W4385966000 creator A5083807807 @default.
- W4385966000 date "2023-08-16" @default.
- W4385966000 modified "2023-09-23" @default.
- W4385966000 title "Episodic Bayesian Optimal Control with Unknown Randomness Distributions" @default.
- W4385966000 doi "https://doi.org/10.48550/arxiv.2308.08478" @default.
- W4385966000 hasPublicationYear "2023" @default.
- W4385966000 type Work @default.
- W4385966000 citedByCount "0" @default.
- W4385966000 crossrefType "posted-content" @default.
- W4385966000 hasAuthorship W4385966000A5025917676 @default.
- W4385966000 hasAuthorship W4385966000A5032561481 @default.
- W4385966000 hasAuthorship W4385966000A5068512850 @default.
- W4385966000 hasAuthorship W4385966000A5083807807 @default.
- W4385966000 hasBestOaLocation W43859660001 @default.
- W4385966000 hasConcept C105795698 @default.
- W4385966000 hasConcept C107673813 @default.
- W4385966000 hasConcept C11413529 @default.
- W4385966000 hasConcept C125112378 @default.
- W4385966000 hasConcept C126255220 @default.
- W4385966000 hasConcept C154945302 @default.
- W4385966000 hasConcept C160234255 @default.
- W4385966000 hasConcept C162324750 @default.
- W4385966000 hasConcept C2777303404 @default.
- W4385966000 hasConcept C33923547 @default.
- W4385966000 hasConcept C41008148 @default.
- W4385966000 hasConcept C50522688 @default.
- W4385966000 hasConcept C57830394 @default.
- W4385966000 hasConceptScore W4385966000C105795698 @default.
- W4385966000 hasConceptScore W4385966000C107673813 @default.
- W4385966000 hasConceptScore W4385966000C11413529 @default.
- W4385966000 hasConceptScore W4385966000C125112378 @default.
- W4385966000 hasConceptScore W4385966000C126255220 @default.
- W4385966000 hasConceptScore W4385966000C154945302 @default.
- W4385966000 hasConceptScore W4385966000C160234255 @default.
- W4385966000 hasConceptScore W4385966000C162324750 @default.
- W4385966000 hasConceptScore W4385966000C2777303404 @default.
- W4385966000 hasConceptScore W4385966000C33923547 @default.
- W4385966000 hasConceptScore W4385966000C41008148 @default.
- W4385966000 hasConceptScore W4385966000C50522688 @default.
- W4385966000 hasConceptScore W4385966000C57830394 @default.
- W4385966000 hasLocation W43859660001 @default.
- W4385966000 hasOpenAccess W4385966000 @default.
- W4385966000 hasPrimaryLocation W43859660001 @default.
- W4385966000 hasRelatedWork W118730952 @default.
- W4385966000 hasRelatedWork W1529069387 @default.
- W4385966000 hasRelatedWork W1997258233 @default.
- W4385966000 hasRelatedWork W2032094637 @default.
- W4385966000 hasRelatedWork W2067883763 @default.
- W4385966000 hasRelatedWork W2617021092 @default.
- W4385966000 hasRelatedWork W2768774425 @default.
- W4385966000 hasRelatedWork W3033856829 @default.
- W4385966000 hasRelatedWork W3210139743 @default.
- W4385966000 hasRelatedWork W1919985504 @default.
- W4385966000 isParatext "false" @default.
- W4385966000 isRetracted "false" @default.
- W4385966000 workType "article" @default.