https://github.com/vfdev-5/rl_interactive
https://github.com/vfdev-5/rl_interactive
Last synced: about 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/vfdev-5/rl_interactive
- Owner: vfdev-5
- Created: 2017-01-24T15:40:40.000Z (over 9 years ago)
- Default Branch: master
- Last Pushed: 2017-03-31T07:53:12.000Z (about 9 years ago)
- Last Synced: 2025-02-08T10:43:48.683Z (over 1 year ago)
- Language: Jupyter Notebook
- Size: 1.92 MB
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Reinforcement Learning *interactive* examples
A number of *jupyter notebooks* introducing basic reinforcement learning algorithms applied on toy models. Algorithms implementations, notations and terms follow ["Reinforcement learning - An introduction" book](https://webdocs.cs.ualberta.ca/~sutton/book/the-book-2nd.html).
## Requirements
* numpy/scipy
* matplotlib
* seaborn
* jupyter-notebook
## Content
* Bridge crossing problem
- Dynamic Programming algorithms (policy iteration, value iteration)
- Monte Carlo methods (first-visit policy evalution, exploring starts, on-policy first-visit)
- Temporal Difference algorithms (SARSA, Q-learning)
* Racecar problem
- Monte Carlo Exploring Starts