https://github.com/seungjaeryanlee/baselines-pytorch

High-quality PyTorch 1.0 implementations of widely used Deep RL algorithms.
https://github.com/seungjaeryanlee/baselines-pytorch

deep-learning deep-reinforcement-learning machine-learning python3 pytorch reinforcement-learning

Last synced: 2 days ago
JSON representation

High-quality PyTorch 1.0 implementations of widely used Deep RL algorithms.

• Host: GitHub
• URL: https://github.com/seungjaeryanlee/baselines-pytorch
• Owner: seungjaeryanlee
• Created: 2018-11-02T00:52:01.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2023-02-10T23:08:35.000Z (almost 2 years ago)
• Last Synced: 2024-05-02T03:46:48.576Z (9 months ago)
• Topics: deep-learning, deep-reinforcement-learning, machine-learning, python3, pytorch, reinforcement-learning
• Language: Python
• Homepage:
• Size: 410 KB
• Stars: 2
• Watchers: 3
• Forks: 0
• Open Issues: 10
• Metadata Files:
  • Readme: README.md
  • Contributing: docs/CONTRIBUTING.md

Awesome Lists containing this project

README

        
# Baselines

[![Build Status](https://travis-ci.com/seungjaeryanlee/baselines.svg?branch=master)](https://travis-ci.com/seungjaeryanlee/baselines)

High-quality modular PyTorch 0.4.1 implementations of widely used Deep RL algorithms.

## Documentations

 - To install necessary packages, check [INSTALLATION.md](docs/INSTALLATION.md).

 - To learn how to use `baselines`, check [USAGE.md](docs/USAGE.md).

 - For a contributor guide, check [CONTRIBUTING.md](docs/CONTRIBUTING.md).

## Algorithms

- [ ] "Naive" DQN

- [x] Vanilla DQN

- [ ] Double DQN

- [ ] Prioritized Experience Replay

- [ ] Dueling DQN

- [ ] Categorical DQN

- [ ] Noisy DQN

- [ ] Rainbow DQN

## Compatible Environments

- [x] CartPole (through OpenAI Gym)

- [x] Arcade Learning Environment (through OpenAI Gym)

- [ ] Super Mario Bros (through Gym Retro)