Markovian Decision Processes with Compact Action Spaces

Online Learning in Markovian Decision Processes

Non-Deterministic Policies in Markovian Decision Processes

Markovian processes have long been used to model stochastic environments. Reinforcement learning has emerged as a framework to solve sequential planning and decision-making problems in such environments. In recent years, attempts were made to apply methods from reinforcement learning to construct decision support systems for action selection in Markovian environments. Although conventional meth...

Feller Processes on Non–locally Compact Spaces

We consider Feller processes on a complete separable metric space X satisfying the ergodic condition of the form lim sup n→∞ ( 1 n n ∑

Perfect equilibrium in games with compact action spaces

We investigate the relations between different types of perfect equilibrium, introduced by Simon and Stinchcombe (1995) for games with compact action spaces and continuous payoffs. Simon and Stinchcombe distinguish two approaches to perfect equilibrium in this context, the classical ”trembling hand” approach, and the so-called ”finitistic” approach. We propose an improved definition of the fini...

Optimality of monotonic policies for two-action Markovian decision processes, with applications to control of queues with delayed information

We consider a discrete-time Markov decision process with a partially ordered state space and two feasible control actions in each state. Our goal is to nd general conditions, which are satissed in a broad class of applications to control of queues, under which an optimal control policy is monotonic. An advantage of our approach is that it easily extends to problems with both information and act...