A Turnpike Theorem For A Risk-Sensitive Markov Decision Process with Stopping
From MaRDI portal
Publication:3427774
DOI10.1137/S0363012904442616zbMath1151.90571MaRDI QIDQ3427774
Uriel G. Rothblum, Eric V. Denardo
Publication date: 27 March 2007
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
stoppingturnpike theoremovertaking optimalityMarkov control processrisk-sensitive dynamic programming
Utility theory (91B16) Dynamic programming (90C39) Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40)
Related Items
Turnpike theorems for Markov games, Discounted approximations to the risk-sensitive average cost in finite Markov chains, The multi-armed bandit, with constraints, Discounted approximations in risk-sensitive average Markov cost chains with finite state space, Turnpikes in Finite Markov Decision Processes and Random Walk, Characterization of the optimal average cost in Markov decision chains driven by a risk-seeking controller, The Vanishing Discount Approach in a class of Zero-Sum Finite Games with Risk-Sensitive Average Criterion, Optimal halting policies in Markov population decision chains with constant risk posture, A discounted approach in communicating average Markov decision chains under risk-aversion, Recursive Markov Decision Processes and Recursive Stochastic Games, Vanishing discount approximations in controlled Markov chains with risk-sensitive average criterion, Characterization of the Optimal Risk-Sensitive Average Cost in Denumerable Markov Decision Chains, Totally expanding multiplicative systems, Constant risk aversion in stochastic contests with exponential completion times
