Reinforcement-Learning - GitLite

KO | EN

gitlite — search

#react #typescript #llm #android #machine-learning #linux #nodejs #macos #awesome #cli #awesome-list #mcp #ios #openai

Reinforcement-Learning

(★ 159)

Implementation of Reinforcement Learning algorithms in Python, based on Sutton's & Barto's Book (Ed. 2)

File Explorer

Download Latest Version (.zip)

- Rl_agent.png
- README.md
- 2.4.pdf
- 2.7.pdf
- action_value.py
- agents.py
- decision_making.py
- Playground Notebook.ipynb
- README.md
- - Policy Evaluation.ipynb
  - Policy Improvement.ipynb
  - Policy Iteration.ipynb
  - Value Iteration.ipynb
- dp.py
- README.md
- - Off-Policy Weighted Importance Sampling Control.ipynb
  - On-Policy First-Visit Average Sampling Control.ipynb
- algorithms.py
- README.md
- - Double-Q-Learning.ipynb
  - Q-Learning.ipynb
  - Sarsa.ipynb
- algorithms.py
- - n-Step Backup Tree.ipynb
  - n-Step Sarsa (Offline with Importance Sampling).ipynb
  - n-Step Sarsa.ipynb
- algorithms.py
- algorithms.py
.gitignore
classes.py
LICENSE
README.md
requirements.txt
utils.py
visualize.py

# Installation Guide

1. Get the code

git clone https://github.com/diegoalejogm/Reinforcement-Learning

Downloads the entire project code from GitHub to your computer.

cd Reinforcement-Learning

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install -r requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

jupyter notebook .

Launches Jupyter in your browser so you can open and run the notebook (.ipynb) files.

✅ If it runs without errors and prints output in the terminal, it worked.

Pulled directly from this repo's README.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Reinforcement-Learning
This repository includes **Python implementations of Sutton's &amp; Barto's Reinforcement Learning Book (Ed. 2) algorithms**. The latest draft of the book's second version can be found in this [link](http://incompleteideas.net/book/the-book-2nd.html ). In this repository you may also find the solutions of the book exercises that I've been implementing.

<img src=".assets/Rl_agent.png" width="550" >

## Structure

### Folder
This repository is divided into **several folders, each for a chapter of the book**. In general, every episode is related to a set of Reinforcement Learning algorithms (e.g. Time Difference Methods).

Additionally, in all chapter-directories, a `notebooks` sub-folder is present. Such files are interactive Jupyter Notebooks, where users can interact with OpenAI environments and the algorithms available.

### Files

The following Python files, found in the home directory, are the most relevant for this project:

[```classes.py```](https://github.com/diegoalejogm/Reinforcement-Learning/blob/master/classes.py)
Contains the implementation of common models used in Reinforcement Learning tasks. An example of this are Policy classes (e.g. e-greedy), Action Value Functions, and relevant data structures (e.g. N-Step Memory).

[```utils.py```](https://github.com/diegoalejogm/Reinforcement-Learning/blob/master/utils.py)
Contains auxiliary methods such as printing and displaying environment interaction logs, which are used by other modules.

[```visualize.py```](https://github.com/diegoalejogm/Reinforcement-Learning/blob/master/visualize.py)
Contains methods that enable the visualization of statistics calculated from the experience of agents that have ran in environments.

## Install

In your terminal, run:

```
git clone git@github.com:diegoalejogm/Reinforcement-Learning.git
cd Reinforcement-Learning
```
Then, install all dependencies with `PIP` using:

```
pip install -r requirements.txt
```

And run a jupyter process in order to visualize and interact with all the available Jupyter notebooks:

```
jupyter notebook .
```

## To Do List
This section is for myself, but feel free to **fork the repo** and add your contributions!

- [ ] Add Tests to Data Structures and Models.

## License
MIT