Least absolute policy iteration for robust value function approximation.
Masashi SugiyamaHirotaka HachiyaHisashi KashimaTetsuro MorimuraPublished in: ICRA (2009)
Keyphrases
- policy iteration
- markov decision processes
- approximate dynamic programming
- temporal difference
- reinforcement learning
- model free
- optimal policy
- fixed point
- sample path
- least squares
- markov decision process
- policy evaluation
- temporal difference learning
- decision making
- function approximation
- basis functions
- linear programming
- state space
- neural network
- linear program
- average cost
- monte carlo
- search space
- discounted reward