Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
Haoran Li, Zhennan Jiang, YUHUI CHEN, Dongbin Zhao
Abstract
With high-dimensional state spaces, visual reinforcement learning (RL) faces significant challenges in exploitation and exploration, resulting in low sample efficiency and training stability. As a time-efficient diffusion model, although consistency models have been validated in online state-based RL, it is still an open question whether it can be extended to visual RL. In this paper, we investigate the impact of non-stationary distribution and the actor-critic framework on consistency policy in online RL, and find that consistency policy was unstable during the training, especially in visual RL with the high-dimensional state space. To this end, we suggest sample-based entropy regularization to stabilize the policy training, and propose a consistency policy with prioritized proximal experience regularization (CP3ER) to improve sample efficiency. CP3ER achieves new state-of-the-art (SOTA) performance in 21 tasks across DeepMind control suite and Meta-world. To our knowledge, CP3ER is the first method to apply diffusion/consistency models to visual RL and demonstrates the potential of consistency models in visual RL.
BibTeX
@inproceedings{
li2024generalizing,
title={Generalizing Consistency Policy to Visual {RL} with Prioritized Proximal Experience Regularization},
author={Haoran Li and Zhennan Jiang and YUHUI CHEN and Dongbin Zhao},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=MOFwt8OeXr}
}