A policy iteration algorithm for Markov decision processes skip-free in one direction.
Joke LambertBenny Van HoudtChris BlondiaPublished in: VALUETOOLS (2007)
Keyphrases
- markov decision processes
- policy iteration algorithm
- policy iteration
- finite state
- state space
- reinforcement learning
- dynamic programming
- optimal policy
- transition matrices
- average reward
- decision processes
- planning under uncertainty
- partially observable
- infinite horizon
- average cost
- markov decision process
- model free
- partially observable markov decision processes
- evaluation function
- stochastic games
- markov decision problems
- actor critic