Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
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.
Code (1)
Tasks
continuous-controlContinuous ControlMuJoCoOffline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
Improving the reasoning capabilities of diffusion-based large language models (dLLMs) through reinforcement learning (RL) remains an open problem. The intractability of dLLMs likelihood function necessitates approximatin…
Reinforcement LearningFlow Matching Policy Gradients
Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement…
Reinforcement LearningContinuous ControlFlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification
Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods. Existing density-approximated policy gradient methods rely on stochastic SDE sa…
Reinforcement LearningPreferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as p…
Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)Energy-Weighted Flow Matching for Offline Reinforcement Learning
This paper investigates energy guidance in generative modeling, where the target distribution is defined as $q(\mathbf x) \propto p(\mathbf x)\exp(-\beta \mathcal E(\mathbf x))$, with $p(\mathbf x)$ being the data distri…
Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)