Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning

This is an official repository of the paper "Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning", which has been presented at NeurIPS-2021.

arXiv version is also available.

It is still under construction.

Referred Codebases

We refer to the following codebases. These repositories are under the MIT license.

• OpenAI Gym
• OpenAI baselines
• Geometric-Primitives

Contact

If you have any questions, please open an issue in this repository, or contact Jungtaek Kim.

Citation

Note that Hyunsoo Chung and Jungtaek Kim equally contributed.

@inproceedings{ChungH2021neurips,
    title={{Brick-by-Brick}: Combinatorial Construction with Deep Reinforcement Learning},
    author={Chung, Hyunsoo and Kim, Jungtaek and Knyazev, Boris and Lee, Jinhwi and Taylor, Graham W. and Park, Jaesik and Cho, Minsu},
    booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
    volume={34},
    year={2021}
}