Lifted-Rollout for Approximate Policy Iteration of Markov Decision Process.
Wang-Zhou DaiYang YuZhi-Hua ZhouPublished in: ICDM Workshops (2011)
Keyphrases
- approximate policy iteration
- markov decision process
- markov games
- policy iteration
- markov decision processes
- reinforcement learning
- state space
- optimal policy
- infinite horizon
- graphical models
- temporal difference learning
- finite horizon
- initial state
- dynamic programming
- reinforcement learning algorithms
- transition probabilities
- state action
- belief propagation
- markov chain
- control problems
- function approximation
- action space
- markov decision problems
- multi agent