Least Absolute Policy Iteration-A Robust Approach to Value Function Approximation.
Masashi SugiyamaHirotaka HachiyaHisashi KashimaTetsuro MorimuraPublished in: IEICE Trans. Inf. Syst. (2010)
Keyphrases
- policy iteration
- markov decision processes
- approximate dynamic programming
- temporal difference
- reinforcement learning
- model free
- temporal difference learning
- fixed point
- optimal policy
- sample path
- markov decision process
- basis functions
- function approximation
- average reward
- markov decision problems
- infinite horizon
- least squares
- state space
- learning algorithm