Linear programming algorithms for semi-Markovian decision processes

Reinforcement Learning Algorithms for Average-Payoff Markovian Decision Processes

Reinforcement learning (RL) has become a central paradigm for solving learning-control problems in robotics and artificial intelligence. R L researchers have focussed almost exclusively on problems where the controller has to maximize the discounted sum of payoffs. However, as emphasized by Schwartz (1$X)3), in many problems, e.g., those for which the optimal behavior is a limit cycle, it is mo...

Existence of Optimal Policies for Semi-Markov Decision Processes Using Duality for Infinite Linear Programming

Semi-Markov decision processes on Borel spaces with deterministic kernels have many practical applications, particularly in inventory theory. Most of the results from general semi-Markov decision processes do not carry over to a deterministic kernel since such a kernel does not provide “smoothness.” We develop infinite dimensional linear programming theory for a general stochastic semi-Markov d...

Constrained Markovian decision processes: the dynamic programming approach

We consider semicontinuous controlled Markov models in discrete time with total expected losses. Only control strategies which meet a set of given constraint inequalities are admissible. One has to build an optimal admissible strategy. The main result consists in the constructive development of optimal strategy with the help of the dynamic programming method. The model studied covers the case o...

Fuzzy Primal Simplex Algorithms for Solving Fuzzy Linear Programming Problems

Approximate Linear Programming for Constrained Partially Observable Markov Decision Processes

In many situations, it is desirable to optimize a sequence of decisions by maximizing a primary objective while respecting some constraints with respect to secondary objectives. Such problems can be naturally modeled as constrained partially observable Markov decision processes (CPOMDPs) when the environment is partially observable. In this work, we describe a technique based on approximate lin...