A simple condition for regularity in negative programming

DOI10.2307/3212899MaRDI QIDQ3851992zbMATH OpenOpenAlexFDO

Authors Peter Whittle

Publication date 1979

Published in Journal of Applied Probability (Search for Journal in Brave)

Full work available at URL https://doi.org/10.2307/3212899

zbMATH Keywords

regularityMarkov decision processesnegative rewardsnegative dynamic programmingbridging conditiondiscrete-time stationary Markovian discounted dynamic program

Mathematics Subject Classification ID

Dynamic programming (90C39) Minimax problems in mathematical programming (90C47)

Cited in

(3)

• A mixed value and policy iteration method for stochastic control with universally measurable policies
• On the convergence of successive approximations in dynamic programming with non-zero terminal reward
• On convergence of value iteration for a class of total cost Markov decision processes

This page was built for publication: A simple condition for regularity in negative programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3851992)