https://github.com/kzl/decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.
https://github.com/kzl/decision-transformer

Last synced: 25 days ago
JSON representation

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

• Host: GitHub
• URL: https://github.com/kzl/decision-transformer
• Owner: kzl
• License: mit
• Created: 2021-06-02T09:35:37.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2024-04-29T01:30:45.000Z (6 months ago)
• Last Synced: 2024-10-01T22:02:02.247Z (about 1 month ago)
• Language: Python
• Size: 256 KB
• Stars: 2,344
• Watchers: 29
• Forks: 446
• Open Issues: 31
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

• awesome-decision-transformer - official - engine](https://github.com/opendilab/DI-engine/blob/main/dizoo/d4rl/entry/d4rl_dt_main.py) (Papers / NeurIPS 2021)
• StarryDivineSky - kzl/decision-transformer

README

        

# Decision Transformer

Lili Chen\*, Kevin Lu\*, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas†, and Igor Mordatch†

\*equal contribution, †equal advising

A link to our paper can be found on [arXiv](https://arxiv.org/abs/2106.01345).

## Overview

Official codebase for [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://sites.google.com/berkeley.edu/decision-transformer).

Contains scripts to reproduce experiments.

![image info](./architecture.png)

## Instructions

We provide code in two sub-directories: `atari` containing code for Atari experiments and `gym` containing code for OpenAI Gym experiments.

See corresponding READMEs in each folder for instructions; scripts should be run from the respective directories.

It may be necessary to add the respective directories to your PYTHONPATH.

## Citation

Please cite our paper as:

```

@article{chen2021decisiontransformer,

  title={Decision Transformer: Reinforcement Learning via Sequence Modeling},

  author={Lili Chen and Kevin Lu and Aravind Rajeswaran and Kimin Lee and Aditya Grover and Michael Laskin and Pieter Abbeel and Aravind Srinivas and Igor Mordatch},

  journal={arXiv preprint arXiv:2106.01345},

  year={2021}

}

```

Note: this is not an official Google or Facebook product.

## License

MIT