Relative Loss Bounds for Temporal-Difference Learning.
Jürgen ForsterManfred K. WarmuthPublished in: Mach. Learn. (2003)
Keyphrases
- loss bounds
- temporal difference learning
- function approximation
- fixed point
- approximate value iteration
- game playing
- evaluation function
- reinforcement learning
- temporal difference
- monte carlo
- reinforcement learning algorithms
- markov decision process
- closed form
- learning tasks
- policy iteration
- function approximators
- sufficient conditions
- expert advice
- state space
- pairwise