Mean Field Approximation of the Policy Iteration Algorithm for Graph-Based Markov Decision Processes.
Nathalie PeyrardRégis SabbadinPublished in: ECAI (2006)
Keyphrases
- markov decision processes
- policy iteration algorithm
- policy iteration
- finite state
- state space
- reinforcement learning
- optimal policy
- dynamic programming
- planning under uncertainty
- transition matrices
- partially observable
- decision processes
- infinite horizon
- reward function
- average cost
- average reward
- markov decision process
- model free