Finite-horizon variance penalised Markov decision processes
نویسنده
چکیده
We consider a finite horizon Markov decision process with only terminal rewards. We describe a finite algorithm for computing a Markov deterministic policy which maximises the variance penalised reward and we outline a vertex elimination algorithm which can reduce the computation involved.
منابع مشابه
Semi-markov Decision Processes
Considered are infinite horizon semi-Markov decision processes (SMDPs) with finite state and action spaces. Total expected discounted reward and long-run average expected reward optimality criteria are reviewed. Solution methodology for each criterion is given, constraints and variance sensitivity are also discussed.
متن کاملAlgorithmic aspects of mean-variance optimization in Markov decision processes
We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove that the complexity of computing a policy that maximizes the mean reward under a variance constraint is NP-hard for some cases, and strongly NP-hard for oth...
متن کاملMean-Variance Optimization in Markov Decision Processes
We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove that the complexity of computing a policy that maximizes the mean reward under a variance constraint is NP-hard for some cases, and strongly NP-hard for oth...
متن کاملLoss Bounds for Uncertain Transition Probabilities in Markov Decision Processes
We analyze losses resulting from uncertain transition probabilities in Markov decision processes with bounded nonnegative rewards. We assume that policies are pre-computed using exact dynamic programming with the estimated transition probabilities, but the system evolves according to different, true transition probabilities. Our approach analyzes the growth of errors incurred by stepping backwa...
متن کاملOn the Undecidability of Probabilistic Planning and Infinite-Horizon Partially Observable Markov Decision Problems
We investigate the computability of problems in probabilistic planning and partially observable infinite-horizon Markov decision processes. The undecidability of the string-existence problem for probabilistic finite automata is adapted to show that the following problem of plan existence in probabilistic planning is undecidable: given a probabilistic planning problem, determine whether there ex...
متن کامل