Metrics for Finite Markov Decision Processes
Norman Ferns, Prakash Panangaden, Doina Precup
We present metrics for measuring the similarity of states in a finite Markov decision process (MDP). The formulation of our metrics is based on the notion of bisimulation for MDPs, with an aim towards solving discounted infinite horizon reinforcement learning tasks. Such metrics can be used to aggregate states, as well as to better structure other value function approximators (e.g., memory-based or nearest-neighbor approximators). We provide bounds that relate our metric distances to the optimal values of states in the given MDP.
PDF Link: /papers/04/p162-ferns.pdf
AUTHOR = "Norman Ferns
and Prakash Panangaden and Doina Precup",
TITLE = "Metrics for Finite Markov Decision Processes",
BOOKTITLE = "Proceedings of the Twentieth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-04)",
PUBLISHER = "AUAI Press",
ADDRESS = "Arlington, Virginia",
YEAR = "2004",
PAGES = "162--169"