Jiajun Fan

ICLR 2023, Oral — Notable Top 5%

Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection

In brief

What the paper does.

We propose LBC (Learnable Behavior Control), a unified framework enabling significantly enlarged behavior selection space via a hybrid behavior mapping. Our agents achieved 10077.52% mean human normalized score and surpassed 24 human world records within 1B training frames, demonstrating SOTA performance with exceptional sample efficiency.

Published in
International Conference on Learning Representations 2023 (ICLR 2023, Oral — Notable Top 5%)
Paper
openreview.net/forum?id=FeWvD0L_a4
Project page
jiajunfan.com/projects/lbc/

Cite

Cite the paper.

@inproceedings{fan2023learnable,
  title={Learnable Behavior Control: Breaking Atari Human World Records
  via Sample-Efficient Behavior Selection},
  author={Jiajun Fan and Yuzheng Zhuang and Yuecheng Liu and Jianye HAO
  and Bin Wang and Jiangcheng Zhu and Hao Wang and Shu-Tao Xia},
  booktitle={The Eleventh International Conference on Learning Representations},
  year={2023},
  url={https://openreview.net/forum?id=FeWvD0L_a4}
}