(Extended version of Memorandum COSOR 81-11) This paper deals with total reward Markov decision processes with countable state space and extends various results on (nearly-)optimal stationary strategies. Strauch proved that if the rewards are nonpositive and the action space is finite then an optimal stationary strategy exists. For the case of nonnegative rewards Ornstein proved the existence of a stationary strategy f which is uniformly nearly-optimal in the multiplicative sense: v(f) = (1 - e) v* . Van der Wal showed that if the action space is finite then for each initial state a stationary nearly-optimal strategy exists. These partial results are connected and extended in the following theorem. If in each state where the value is nonpos...
We deal with stochastic games with finite state and action spaces for which we examine players' poss...
We consider positive zero-sum stochastic games with countable state and action spaces. For each play...
We consider a discrete time Markov Decision Process with infinite horizon. The criterion to be maxim...
For Markov decision processes with countable state space and nonnegative immediate rewards Ornstein ...
This paper gives a systematic treatment of results about the existence of various types of nearly-op...
Consider a Markov decision process with countable state space S and finite action space A. If in sta...
In this paper the following result is proved. In any total reward countable state Markov decision pr...
We examine the use of stationary and Markov strategies in zero-sum stochastic games with finite stat...
We are interested in the existence of pure and stationary optimal strategies in Markov decision proc...
AbstractThis paper deals with a discrete time Markov decision model with a finite state space, arbit...
Abstract. We deal with zero-sum limiting average stochastic games. We show that the existence of arb...
In every finite-state leavable gambling problem and in every finite-state Markov decision process wi...
In this paper we show that the existence of p-equilibrium stationary strategies imply the existence ...
AbstractFor countable-state decision processes (dynamic programming problems), a general class of ob...
In this paper we prove the existence of p-equilibrium stationary strategies for non-zero-sum stochas...
We deal with stochastic games with finite state and action spaces for which we examine players' poss...
We consider positive zero-sum stochastic games with countable state and action spaces. For each play...
We consider a discrete time Markov Decision Process with infinite horizon. The criterion to be maxim...
For Markov decision processes with countable state space and nonnegative immediate rewards Ornstein ...
This paper gives a systematic treatment of results about the existence of various types of nearly-op...
Consider a Markov decision process with countable state space S and finite action space A. If in sta...
In this paper the following result is proved. In any total reward countable state Markov decision pr...
We examine the use of stationary and Markov strategies in zero-sum stochastic games with finite stat...
We are interested in the existence of pure and stationary optimal strategies in Markov decision proc...
AbstractThis paper deals with a discrete time Markov decision model with a finite state space, arbit...
Abstract. We deal with zero-sum limiting average stochastic games. We show that the existence of arb...
In every finite-state leavable gambling problem and in every finite-state Markov decision process wi...
In this paper we show that the existence of p-equilibrium stationary strategies imply the existence ...
AbstractFor countable-state decision processes (dynamic programming problems), a general class of ob...
In this paper we prove the existence of p-equilibrium stationary strategies for non-zero-sum stochas...
We deal with stochastic games with finite state and action spaces for which we examine players' poss...
We consider positive zero-sum stochastic games with countable state and action spaces. For each play...
We consider a discrete time Markov Decision Process with infinite horizon. The criterion to be maxim...