An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning.
Richard S. SuttonAshique Rupam MahmoodMartha WhitePublished in: J. Mach. Learn. Res. (2016)
Keyphrases
- temporal difference learning
- fixed point
- function approximation
- evaluation function
- approximate value iteration
- game playing
- reinforcement learning
- temporal difference
- reinforcement learning algorithms
- markov decision process
- monte carlo
- policy iteration
- function approximators
- video games
- neural network
- action selection
- active learning