On Generalized Bellman Equations and Temporal-Difference Learning.
Huizhen YuAshique Rupam MahmoodRichard S. SuttonPublished in: J. Mach. Learn. Res. (2018)
Keyphrases
- temporal difference learning
- fixed point
- function approximation
- reinforcement learning
- game playing
- evaluation function
- approximate value iteration
- temporal difference
- markov decision process
- reinforcement learning algorithms
- monte carlo
- function approximators
- markov decision processes
- markov random field
- state space
- policy iteration
- neural network