A simple condition for regularity in negative programming

DOI10.2307/3212899zbMath0418.90085OpenAlexW4249418023MaRDI QIDQ3851992

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

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

Related Items (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