AbstractFor countable-state decision processes (dynamic programming problems), a general class of objective functions is identified for which it is shown that good Markov strategies always exist. This class includes product and lim inf rewards, as well as practically all the classical dynamic programming expected payoff functions
We consider finite horizon Markov decision processes under performance measures that involve both th...
We consider the relationship between the reward function and the existence of (nearly) optimal Marko...
AbstractIn the present paper the expected average reward criterion is considered instead of the aver...
AbstractFor countable-state decision processes (dynamic programming problems), a general class of ob...
What are the functionals of the reward that can be computed and optimized exactly in Markov Decision...
AbstractThis paper deals with a discrete time Markov decision model with a finite state space, arbit...
This paper gives a systematic treatment of results about the existence of various types of nearly-op...
The theory of Markov Decision Processes is the theory of controlled Markov chains. Its origins can b...
AbstractIn a decision process (gambling or dynamic programming problem) with finite state space and ...
In several standard models of dynamic programming (gambling houses, MDPs, POMDPs), we prove the exis...
We study the existence of optimal strategies and value function of non stationary Markov decision pr...
In this paper the following result is proved. In any total reward countable state Markov decision pr...
(Extended version of Memorandum COSOR 81-11) This paper deals with total reward Markov decision proc...
We study Markov decision processes (MDPs) with multiple limit-average (or mean-payoff) functions. We...
We study countably infinite Markov decision processes (MDPs) with real-valued transition rewards. Ev...
We consider finite horizon Markov decision processes under performance measures that involve both th...
We consider the relationship between the reward function and the existence of (nearly) optimal Marko...
AbstractIn the present paper the expected average reward criterion is considered instead of the aver...
AbstractFor countable-state decision processes (dynamic programming problems), a general class of ob...
What are the functionals of the reward that can be computed and optimized exactly in Markov Decision...
AbstractThis paper deals with a discrete time Markov decision model with a finite state space, arbit...
This paper gives a systematic treatment of results about the existence of various types of nearly-op...
The theory of Markov Decision Processes is the theory of controlled Markov chains. Its origins can b...
AbstractIn a decision process (gambling or dynamic programming problem) with finite state space and ...
In several standard models of dynamic programming (gambling houses, MDPs, POMDPs), we prove the exis...
We study the existence of optimal strategies and value function of non stationary Markov decision pr...
In this paper the following result is proved. In any total reward countable state Markov decision pr...
(Extended version of Memorandum COSOR 81-11) This paper deals with total reward Markov decision proc...
We study Markov decision processes (MDPs) with multiple limit-average (or mean-payoff) functions. We...
We study countably infinite Markov decision processes (MDPs) with real-valued transition rewards. Ev...
We consider finite horizon Markov decision processes under performance measures that involve both th...
We consider the relationship between the reward function and the existence of (nearly) optimal Marko...
AbstractIn the present paper the expected average reward criterion is considered instead of the aver...
DOI
Add to ORKG