Corpus ID: 232146715

Behavior From the Void: Unsupervised Active Pre-Training

@article{Liu2021BehaviorFT,
  title={Behavior From the Void: Unsupervised Active Pre-Training},
  author={Hao Liu and P. Abbeel},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.04551}
}
We introduce a new unsupervised pre-training method for reinforcement learning called APT, which stands for Active Pre-Training. APT learns behaviors and representations by actively searching for novel states in reward-free environments. The key novel idea is to explore the environment by maximizing a non-parametric entropy computed in an abstract representation space, which avoids the challenging density modeling and consequently allows our approach to scale much better in environments that… Expand