Multi-Timescale, Gradient Descent, Temporal Difference Learning with Linear Options.
Peeyush KumarDoina PrecupPublished in: CoRR (2017)
Keyphrases
- temporal difference learning
- temporal difference learning algorithms
- fixed point
- function approximation
- reinforcement learning
- game playing
- evaluation function
- function approximators
- temporal difference
- cost function
- approximate value iteration
- monte carlo
- markov decision process
- loss function
- neural network
- learning experience
- learning algorithm