The script needs the RandomWalk environment.
- Reinforcement Learning: An Introduction
by Richard S. Sutton and Andrew G. Barto
- TD(0) Algorithm: Chapter 6, equation 6.2.
- RandomWalk example: Chapter 6, example 6.2.
td0_implementation
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|
parent directory.. | ||||