https://github.com/zakaria-narjis/modularl

A highly modular and extensible PyTorch-based reinforcement learning library.
https://github.com/zakaria-narjis/modularl

deep-learning deep-reinforcement-learning pytroch reinforcement-learning torchrl

Last synced: 4 months ago
JSON representation

A highly modular and extensible PyTorch-based reinforcement learning library.

• Host: GitHub
• URL: https://github.com/zakaria-narjis/modularl
• Owner: zakaria-narjis
• License: mit
• Created: 2024-07-31T15:38:08.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-08-09T22:59:15.000Z (almost 2 years ago)
• Last Synced: 2024-08-10T02:14:06.931Z (almost 2 years ago)
• Topics: deep-learning, deep-reinforcement-learning, pytroch, reinforcement-learning, torchrl
• Language: Python
• Homepage: https://modularl.readthedocs.io/en/latest/#
• Size: 546 KB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# ModulaRL



  





  🚧 This library is still under construction. 🚧



[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)

[![pytest](https://img.shields.io/badge/tested%20with-pytest-46a2f1.svg)](https://docs.pytest.org/en/stable/)

[![Documentation Status](https://readthedocs.org/projects/modularl/badge/?version=latest)](https://modularl.readthedocs.io/en/latest/?badge=latest)

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

ModulaRL is a highly modular and extensible reinforcement learning library built on PyTorch. It aims to provide researchers and developers with a flexible framework for implementing, experimenting with, and extending various RL algorithms.

## Features

- Modular architecture allowing easy component swapping and extension

- Efficient implementations leveraging PyTorch's capabilities

- Integration with TorchRL for optimized replay buffers

- Clear documentation and examples for quick start

- Designed for both research and practical applications in reinforcement learning

## TODO

  - Add new algorithms

  - Add exploration modules

  - Add experiment wrapper modules

  

## Installation

```bash

pip install modularl

```

## Algorithms Implemented

| Algorithm                  | Type       | Paper                                               | Continuous Action | Discrete Action      |

|----------------------------|------------|-----------------------------------------------------|-------------------|----------------------|

| SAC (Soft Actor-Critic)    | Off-policy | [Haarnoja et al. 2018](https://arxiv.org/abs/1801.01290) | ✅                 | Not implemented YET  |

| TD3 (Twin Delayed DDPG)    | Off-policy | [Fujimoto et al. 2018](https://arxiv.org/abs/1802.09477) | ✅                 | Not implemented YET  |

| DDPG (Deep Deterministic Policy Gradient) | Off-policy | [Lillicrap et al. 2015](https://arxiv.org/abs/1509.02971) | ✅                 | Not implemented YET  |

## Citation

```

@software{modularl2024,

  author = {zakaria narjis},

  title = {ModulaRL: A Modular Reinforcement Learning Library},

  year = {2024},

  url = {https://github.com/zakaria-narjis/modularl}

}

```