Finite Markov Decision Process
(Redirected from finite Markov decision process (MDP))
Jump to navigation
Jump to search
A Finite Markov Decision Process is a Markov decision process that is finite.
- …
- Counter-Example(s):
- See: Q-Learning.
References
2004
- (Ferns et al., 2004) ⇒ Norm Ferns, Prakash Panangaden, and Doina Precup. (2004). “Metrics for Finite Markov Decision Processes.” In: Proceedings of the 20th conference on Uncertainty in artificial intelligence, pp. 162-169 . AUAI Press,
- ABSTRACT: 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.