On Generalized Bellman Equations and Temporal-Difference Learning.
Huizhen YuAshique Rupam MahmoodRichard S. SuttonPublished in: CoRR (2017)
Keyphrases
- temporal difference learning
- function approximation
- fixed point
- evaluation function
- game playing
- reinforcement learning
- temporal difference
- approximate value iteration
- markov decision process
- reinforcement learning algorithms
- policy iteration
- neural network
- cost function
- least squares
- sufficient conditions
- model free