A Universal Empirical Dynamic Programming Algorithm for Continuous State MDPs

DOI10.1109/TAC.2019.2907414MaRDI QIDQ5211320zbMATH OpenOpenAlexWikidataFDO

Authors William B. Haskell, Rahul Jain, Hiteshi Sharma, Pengqian Yu

Publication date 28 January 2020

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tac.2019.2907414

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Cited in

(4)

• Robustness to incorrect models and data-driven learning in average-cost optimal stochastic control
• Some limit properties of Markov chains induced by recursive stochastic algorithms
• Error analysis for approximate CVaR-optimal control with a maximum cost
• A convex optimization approach to dynamic programming in continuous state and action spaces

This page was built for publication: A Universal Empirical Dynamic Programming Algorithm for Continuous State MDPs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5211320)