Ecosyste.ms: Awesome

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

Awesome Lists | Featured Topics | Projects

https://github.com/Curt-Park/rainbow-is-all-you-need

Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow
https://github.com/Curt-Park/rainbow-is-all-you-need

colab-notebook dqn gym-environment nbviewer pytorch rainbow reinforcement-learning

Last synced: 10 days ago
JSON representation

Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow

Host: GitHub
URL: https://github.com/Curt-Park/rainbow-is-all-you-need
Owner: Curt-Park
License: mit
Created: 2019-06-10T09:06:10.000Z (over 5 years ago)
Default Branch: master
Last Pushed: 2024-01-19T21:12:17.000Z (10 months ago)
Last Synced: 2024-06-20T00:00:54.064Z (5 months ago)
Topics: colab-notebook, dqn, gym-environment, nbviewer, pytorch, rainbow, reinforcement-learning
Language: Jupyter Notebook
Homepage:
Size: 8.6 MB
Stars: 1,787
Watchers: 26
Forks: 335
Open Issues: 4
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

awesome-google-colab - DQN to Rainbow - A step-by-step tutorial from DQN to Rainbow (Technologies)

README

        [![All Contributors](https://img.shields.io/badge/all_contributors-6-orange.svg?style=flat-square)](#contributors)

*Do you want a RL agent nicely moving on Atari?*

# Rainbow is all you need!

This is a step-by-step tutorial from DQN to Rainbow.

Every chapter contains both of theoretical backgrounds and object-oriented implementation. Just pick any topic in which you are interested, and learn! You can execute them right away with Colab even on your smartphone.

Please feel free to open an issue or a pull-request if you have any idea to make it better. :)

>If you want a tutorial for policy gradient methods, please see [PG is All You Need](https://github.com/MrSyee/pg-is-all-you-need).

## Contents

01. DQN [[NBViewer](https://nbviewer.jupyter.org/github/Curt-Park/rainbow-is-all-you-need/blob/master/01.dqn.ipynb)] [[Colab](https://colab.research.google.com/github/Curt-Park/rainbow-is-all-you-need/blob/master/01.dqn.ipynb)]

02. DoubleDQN [[NBViewer](https://nbviewer.jupyter.org/github/Curt-Park/rainbow-is-all-you-need/blob/master/02.double_q.ipynb)] [[Colab](https://colab.research.google.com/github/Curt-Park/rainbow-is-all-you-need/blob/master/02.double_q.ipynb)]

03. PrioritizedExperienceReplay [[NBViewer](https://nbviewer.jupyter.org/github/Curt-Park/rainbow-is-all-you-need/blob/master/03.per.ipynb)] [[Colab](https://colab.research.google.com/github/Curt-Park/rainbow-is-all-you-need/blob/master/03.per.ipynb)]

04. DuelingNet [[NBViewer](https://nbviewer.jupyter.org/github/Curt-Park/rainbow-is-all-you-need/blob/master/04.dueling.ipynb)] [[Colab](https://colab.research.google.com/github/Curt-Park/rainbow-is-all-you-need/blob/master/04.dueling.ipynb)]

05. NoisyNet [[NBViewer](https://nbviewer.jupyter.org/github/Curt-Park/rainbow-is-all-you-need/blob/master/05.noisy_net.ipynb)] [[Colab](https://colab.research.google.com/github/Curt-Park/rainbow-is-all-you-need/blob/master/05.noisy_net.ipynb)]

06. CategoricalDQN [[NBViewer](https://nbviewer.jupyter.org/github/Curt-Park/rainbow-is-all-you-need/blob/master/06.categorical_dqn.ipynb)] [[Colab](https://colab.research.google.com/github/Curt-Park/rainbow-is-all-you-need/blob/master/06.categorical_dqn.ipynb)]

07. N-stepLearning [[NBViewer](https://nbviewer.jupyter.org/github/Curt-Park/rainbow-is-all-you-need/blob/master/07.n_step_learning.ipynb)] [[Colab](https://colab.research.google.com/github/Curt-Park/rainbow-is-all-you-need/blob/master/07.n_step_learning.ipynb)]

08. Rainbow [[NBViewer](https://nbviewer.jupyter.org/github/Curt-Park/rainbow-is-all-you-need/blob/master/08.rainbow.ipynb)] [[Colab](https://colab.research.google.com/github/Curt-Park/rainbow-is-all-you-need/blob/master/08.rainbow.ipynb)]

## Prerequisites

This repository is tested with python 3.8+

```

git clone https://github.com/Curt-Park/rainbow-is-all-you-need.git

cd rainbow-is-all-you-need

make setup

```

## How to Run

```

jupyter lab

```

## Related Papers

01. [V. Mnih et al., "Human-level control through deep reinforcement learning." Nature, 518

(7540):529–533, 2015.](https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf)

02. [van Hasselt et al., "Deep Reinforcement Learning with Double Q-learning." arXiv preprint arXiv:1509.06461, 2015.](https://arxiv.org/pdf/1509.06461.pdf)

03. [T. Schaul et al., "Prioritized Experience Replay." arXiv preprint arXiv:1511.05952, 2015.](https://arxiv.org/pdf/1511.05952.pdf)

04. [Z. Wang et al., "Dueling Network Architectures for Deep Reinforcement Learning." arXiv preprint arXiv:1511.06581, 2015.](https://arxiv.org/pdf/1511.06581.pdf)

05. [M. Fortunato et al., "Noisy Networks for Exploration." arXiv preprint arXiv:1706.10295, 2017.](https://arxiv.org/pdf/1706.10295.pdf)

06. [M. G. Bellemare et al., "A Distributional Perspective on Reinforcement Learning." arXiv preprint arXiv:1707.06887, 2017.](https://arxiv.org/pdf/1707.06887.pdf)

07. [R. S. Sutton, "Learning to predict by the methods of temporal differences." Machine learning, 3(1):9–44, 1988.](http://incompleteideas.net/papers/sutton-88-with-erratum.pdf)

08. [M. Hessel et al., "Rainbow: Combining Improvements in Deep Reinforcement Learning." arXiv preprint arXiv:1710.02298, 2017.](https://arxiv.org/pdf/1710.02298.pdf)

## Contributors

Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):

  

    

      
_{Jinwoo Park (Curt)}
💻 📖

      
_{Kyunghwan Kim}
💻

      
_{Wei Chen}
🚧

      
_{WANG Lei}
🚧

      
_leeyaf
💻

      
_ahmadF
📖

      
_{Roberto Schiavone}
💻

    

    

      
_{David Yuan}
💻

      
_{dhanushka2001}
💻

    

  

This project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome!