Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow

This repository contains the code implementation of the experiments presented in the paper Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow.

---

Directory Structure

• Use the code in meow/toy to reproduce the experimental results presented in Section 4.1 of our paper.
• Use the code in meow/cleanrl to reproduce the experimental results presented in Section 4.2 of our paper.
• Use the code in meow/skrl to reproduce the experimental results presented in Section 4.3 of our paper.
• Use the code in meow/plot to reproduce the figures presented in our paper.

---

License

To maintain reproducibility, we freezed the released versions of following repositories and list their licenses as follows:

• Toni-SM/skrl (at commit 631613a) is licensed under the MIT License.
• vwxyzjn/cleanrl (at commit 8cbca61) is licensed under the MIT License.
• VincentStimper/normalizing-flows (at commit 848277e) is licensed under the MIT License.
• rail-berkeley/softlearning (at commit 13cf187) is licensed under the MIT License.

Further changes based on the repository above are licensed under the MIT License.

---

Cite this Repository

If you find this repository useful, please consider citing our paper:

@misc{chao2024maximum,
      title={{Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow}}, 
      author={Chen-Hao Chao and Chien Feng and Wei-Fang Sun and Cheng-Kuang Lee and Simon See and Chun-Yi Lee},
      year={2024},
      eprint={2405.13629},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

---

Contributors of the Code Implementation

Visit our GitHub pages by clicking the images above.