Discounted MDP's: distribution functions and exponential utility maximization
SIAM Journal on Control and Optimization
An analysis of stochastic shortest path problems
Mathematics of Operations Research
Risk sensitive control of Markov processes in countable state space
Systems & Control Letters
Stochastic Shortest Path Games
SIAM Journal on Control and Optimization
Optimal Control: Basics and Beyond
Optimal Control: Basics and Beyond
Brief Risk-sensitive and minimax control of discrete-time, finite-state Markov decision processes
Automatica (Journal of IFAC)
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1
Functional value iteration for decision-theoretic planning with general utility functions
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Risk-sensitive planning with one-switch utility functions: value iteration
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Shortest stochastic path with risk sensitive evaluation
MICAI'12 Proceedings of the 11th Mexican international conference on Advances in Artificial Intelligence - Volume Part I
Hi-index | 22.14 |
We consider a class of terminating Markov decision processes with an exponential risk-averse objective function and compact constraint sets. We assume the existence of an absorbing cost-free terminal state @W, positive transition costs and continuity of the transition probability and cost functions. Without discounting future costs in the argument of the exponential utility function, we establish (i) the existence of a real-valued optimal cost function which can be achieved by a stationary policy and (ii) the convergence of value iteration and policy iteration to the unique solution of Bellman's equation. We illustrate the results with two computational examples.