Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization

TL;DR

This paper introduces CP3ER, a novel method applying consistency models to visual reinforcement learning, enhancing sample efficiency and training stability in high-dimensional visual tasks, and achieving state-of-the-art results.

Contribution

It is the first to extend diffusion/consistency models to visual RL, proposing prioritized proximal experience regularization for improved stability and efficiency.

Findings

CP3ER outperforms previous methods on 21 tasks.

Sample-based entropy regularization stabilizes training.

Achieves state-of-the-art performance in visual RL benchmarks.

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. More visualization results are available at https://jzndd.github.io/CP3ER-Page/.