Markov Decision Process (MDP) Toolbox for Matlab

Written by Kevin Murphy, 1999 Last updated: 23 October, 2002. This toolbox supports value and policy iteration for discrete MDPs, and includes some grid-world examples from the textbooks by Sutton and Barto, and Russell and Norvig. It does not implement reinforcement learning or POMDPs. For a very similar package, see INRA's matlab MDP toolbox. Download toolbox A brief introduction to MDPs, POMDPs

[ymiyata3]

Reinforcement Learning, Markov Decision Processes