https://github.com/geyang/rl-playground

Collection of RL algorithm implementations and baselines
https://github.com/geyang/rl-playground

Last synced: 3 months ago
JSON representation

Collection of RL algorithm implementations and baselines

• Host: GitHub
• URL: https://github.com/geyang/rl-playground
• Owner: geyang
• License: mit
• Created: 2020-07-31T19:08:10.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2022-02-16T05:45:09.000Z (over 3 years ago)
• Last Synced: 2025-01-10T12:58:29.115Z (5 months ago)
• Language: Jupyter Notebook
• Size: 53.3 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Welcome to RL-Playground!

This repo contains implementation and baselines for the following algorithms:

- [x] DQN

- [x] Proximal Policy Optimization (PPO)

- [x] Soft Actor-Critic (SAC)

- [x] Twin Delayed DDPG (TD3)

Missing Pieces:

- [ ] hindsight experience replay

- [ ] pixel input

## Citation

If RL Playground has helped in accelerating the publication of your

paper, please kindly consider citing this repo with the following

bibtext entry:

```bibtex

@misc{yang2020playground,

  author={Ge Yang},

  title={Playground},

  url={https://github.com/geyang/rl_playground},

  year={2019}

}

```