Nature

Markov Decision Processes and Stochastic Control

Markov decision processes (MDPs) and stochastic control constitute pivotal frameworks for modelling decision-making in systems subject to uncertainty. At their core, MDPs provide a structured means to ...
Nature

Probabilistic Model Checking and Markov Decision Processes

Probabilistic model checking and Markov decision processes (MDPs) form two interlinked branches of formal analysis for systems operating under uncertainty. These techniques offer a mathematical ...
JSTOR Daily

Performance Guarantees for Empirical Markov Decision Processes with Applications to Multiperiod Inventory Models

We consider Markov decision processes with unknown transition probabilities and unknown single-period expected cost functions, and we study a method for estimating these quantities from historical or ...
JSTOR Daily

Markov Decision Problems Where Means Bound Variances

We identify a rich class of finite-horizon Markov decision problems (MDPs) for which the variance of the optimal total reward can be bounded by a simple linear function of its expected value. The ...