Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/dps0340/dqndemo

Deep Q-Learning from Demonstrations implementation using Pytorch & OpenAI Gym
https://github.com/dps0340/dqndemo

dqn dqn-pytorch openai-gym reinforcement-learning

Last synced: 3 months ago
JSON representation

Deep Q-Learning from Demonstrations implementation using Pytorch & OpenAI Gym

Awesome Lists containing this project

README

        

Welcome to DQNDemo 👋




GitHub

> Deep Q-Learning from Demonstrations implementation using Pytorch & OpenAI Gym

[Paper link](2018-Deep_Q-Learning_from_Demonstrations-AAAI-406.pdf)

## Install

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

## Usage

```sh
python agent_1.py
```

## 🤝 Contributing

Contributions, issues and feature requests are welcome.

Feel free to check [issues page](https://github.com/DPS0340/DQNDemo/issues) if you want to contribute.

## Demo
![DQNDemo](https://user-images.githubusercontent.com/32592965/109403989-09729100-79a5-11eb-95eb-f2327e3078b9.gif)

## Output Graph
![simple DQN](https://github.com/DPS0340/DQNDemo/blob/master/plot_use_per_False.png)
![original DQN](https://github.com/DPS0340/DQNDemo/blob/master/plot_use_per_True.png)

### Simple vs Original

Simple DQN does not have PER algorithm, it selects from uniform distribution.\
Original is vice versa.

## Author

👤 **jiho lee**

* Github: [@DPS0340](https://github.com/DPS0340)

## Show your support

Give a ⭐️ if this project helped you!

***
_This README was generated with ❤️ by [readme-md-generator](https://github.com/kefranabg/readme-md-generator)_