Least-Squares Policy Iteration.
Michail G. LagoudakisRonald ParrPublished in: J. Mach. Learn. Res. (2003)
Keyphrases
- policy iteration
- model free
- temporal difference
- reinforcement learning methods
- reinforcement learning algorithms
- finite sample
- reinforcement learning
- markov decision processes
- state action
- continuous state spaces
- dynamical systems
- cooperative
- evaluation function
- function approximation
- real time
- monte carlo
- statistical learning theory
- linear programming
- state space
- control system
- learning algorithm