Supplementary material for Uncorrected least-squares temporal difference with lambda-return.
Takayuki OsogamiPublished in: CoRR (2019)
Keyphrases
- temporal difference
- least squares
- policy evaluation
- td learning
- reinforcement learning
- function approximation
- evaluation function
- policy iteration
- monte carlo
- model free
- step size
- temporal difference learning
- action selection
- reinforcement learning algorithms
- temporal difference methods
- optical flow
- actor critic
- learning algorithm
- supervised learning
- learning tasks
- fixed point
- markov decision processes
- function approximators
- feature space