Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization

TL;DR

This paper introduces QVPO, a novel diffusion-based online reinforcement learning algorithm that enhances exploration and multimodality, achieving state-of-the-art results on MuJoCo benchmarks.

Contribution

It proposes a new Q-weighted variational loss for diffusion policies in online RL, addressing optimization challenges and improving exploration and sample efficiency.

Findings

QVPO achieves state-of-the-art performance on MuJoCo benchmarks.

The Q-weighted variational loss provides a tight lower bound for policy optimization.

Enhanced exploration capabilities lead to better cumulative rewards.

Abstract

Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the performance of RL algorithms in continuous control tasks by overcoming the limitations of unimodal policies, such as Gaussian policies, and providing the agent with enhanced exploration capabilities. However, existing works mainly focus on the application of diffusion policies in offline RL, while their incorporation into online RL is less investigated. The training objective of the diffusion model, known as the variational lower bound, cannot be optimized directly in online RL due to the unavailability of 'good' actions. This leads to difficulties in conducting diffusion policy improvement. To overcome this, we propose a novel model-free diffusion-based online RL algorithm, Q-weighted Variational Policy Optimization (QVPO). Specifically, we introduce the Q-weighted variational loss, which can be proved to be a tight lower bound of the policy objective in online RL under certain conditions. To fulfill these conditions, the Q-weight transformation functions are introduced for general scenarios. Additionally, to further enhance the exploration capability of the diffusion policy, we design a special entropy regularization term. We also develop an efficient behavior policy to enhance sample efficiency by reducing the variance of the diffusion policy during online interactions. Consequently, the QVPO algorithm leverages the exploration capabilities and multimodality of diffusion policies, preventing the RL agent from converging to a sub-optimal policy. To verify the effectiveness of QVPO, we conduct comprehensive experiments on MuJoCo benchmarks. The final results demonstrate that QVPO achieves state-of-the-art performance on both cumulative reward and sample efficiency.