Efficient Online Reinforcement Learning for Diffusion Policy

• URL: http://arxiv.org/abs/2502.00361v4
• Date: Mon, 30 Jun 2025 03:48:44 GMT
• Title: Efficient Online Reinforcement Learning for Diffusion Policy
• Authors: Haitong Ma, Tianyi Chen, Kai Wang, Na Li, Bo Dai,
• Abstract summary: We generalize the conventional denoising score matching by reweighting the loss function.<n>The resulting Reweighted Score Matching (RSM) preserves the optimal solution and low computational cost.<n>We introduce two practical algorithms named Diffusion Policy Mirror Descent (DPMD) and Soft Diffusion Actor-Critic (SDAC)
• Score: 38.39095131927252
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion policies have achieved superior performance in imitation learning and offline reinforcement learning (RL) due to their rich expressiveness. However, the conventional diffusion training procedure requires samples from target distribution, which is impossible in online RL since we cannot sample from the optimal policy. Backpropagating policy gradient through the diffusion process incurs huge computational costs and instability, thus being expensive and not scalable. To enable efficient training of diffusion policies in online RL, we generalize the conventional denoising score matching by reweighting the loss function. The resulting Reweighted Score Matching (RSM) preserves the optimal solution and low computational cost of denoising score matching, while eliminating the need to sample from the target distribution and allowing learning to optimize value functions. We introduce two tractable reweighted loss functions to solve two commonly used policy optimization problems, policy mirror descent and max-entropy policy, resulting in two practical algorithms named Diffusion Policy Mirror Descent (DPMD) and Soft Diffusion Actor-Critic (SDAC). We conducted comprehensive comparisons on MuJoCo benchmarks. The empirical results show that the proposed algorithms outperform recent diffusion-policy online RLs on most tasks, and the DPMD improves more than 120% over soft actor-critic on Humanoid and Ant.

Related papers

• One-Step Flow Policy Mirror Descent [38.39095131927252]
  Flow Policy Mirror Descent (FPMD) is an online RL algorithm that enables 1-step sampling during policy inference.<n>Our approach exploits a theoretical connection between the distribution variance and the discretization error of single-step sampling in straight flow matching models.
  arXiv  Detail & Related papers  (2025-07-31T15:51:10Z)
• Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone [72.17534881026995]
  We develop an offline and online fine-tuning approach called policy-agnostic RL (PA-RL) We show the first result that successfully fine-tunes OpenVLA, a 7B generalist robot policy, autonomously with Cal-QL, an online RL fine-tuning algorithm.
  arXiv  Detail & Related papers  (2024-12-09T17:28:03Z)
• CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning [25.071018803326254]
  Distribution shift is a major obstacle in offline reinforcement learning. Previous conservative offline RL algorithms struggle to generalize to unseen actions. We propose to use the gradient fields of the dataset density generated from a pre-trained offline RL algorithm to adjust the original actions.
  arXiv  Detail & Related papers  (2024-06-11T17:59:29Z)
• Diffusion Policies creating a Trust Region for Offline Reinforcement Learning [66.17291150498276]
  We introduce a dual policy approach, Diffusion Trusted Q-Learning (DTQL), which comprises a diffusion policy for pure behavior cloning and a practical one-step policy. DTQL eliminates the need for iterative denoising sampling during both training and inference, making it remarkably computationally efficient. We show that DTQL could not only outperform other methods on the majority of the D4RL benchmark tasks but also demonstrate efficiency in training and inference speeds.
  arXiv  Detail & Related papers  (2024-05-30T05:04:33Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization [55.97310586039358]
  Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality.<n>We propose a novel model-free diffusion-based online RL algorithm, Q-weighted Variational Policy Optimization (QVPO)<n>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.<n>We also develop an efficient behavior policy to enhance sample efficiency by reducing the variance of the diffusion policy during online interactions.
  arXiv  Detail & Related papers  (2024-05-25T10:45:46Z)
• Diffusion Actor-Critic with Entropy Regulator [32.79341490514616]
  We propose an online RL algorithm termed diffusion actor-critic with entropy regulator (DACER) This algorithm conceptualizes the reverse process of the diffusion model as a novel policy function. Experiments on MuJoCo benchmarks and a multimodal task demonstrate that the DACER algorithm achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2024-05-24T03:23:27Z)
• Score Regularized Policy Optimization through Diffusion Behavior [25.926641622408752]
  Recent developments in offline reinforcement learning have uncovered the immense potential of diffusion modeling. We propose to extract an efficient deterministic inference policy from critic models and pretrained diffusion behavior models. Our method boosts action sampling speed by more than 25 times compared with various leading diffusion-based methods in locomotion tasks.
  arXiv  Detail & Related papers  (2023-10-11T08:31:26Z)
• Policy Representation via Diffusion Probability Model for Reinforcement Learning [67.56363353547775]
  We build a theoretical foundation of policy representation via the diffusion probability model. We present a convergence guarantee for diffusion policy, which provides a theory to understand the multimodality of diffusion policy. We propose the DIPO which is an implementation for model-free online RL with DIffusion POlicy.
  arXiv  Detail & Related papers  (2023-05-22T15:23:41Z)
• Offline Policy Optimization in RL with Variance Regularizaton [142.87345258222942]
  We propose variance regularization for offline RL algorithms, using stationary distribution corrections. We show that by using Fenchel duality, we can avoid double sampling issues for computing the gradient of the variance regularizer. The proposed algorithm for offline variance regularization (OVAR) can be used to augment any existing offline policy optimization algorithms.
  arXiv  Detail & Related papers  (2022-12-29T18:25:01Z)
• Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning [70.20191211010847]
  Offline reinforcement learning (RL) aims to learn an optimal policy using a previously collected static dataset. We introduce Diffusion Q-learning (Diffusion-QL) that utilizes a conditional diffusion model to represent the policy. We show that our method can achieve state-of-the-art performance on the majority of the D4RL benchmark tasks.
  arXiv  Detail & Related papers  (2022-08-12T09:54:11Z)
• Mixed Reinforcement Learning with Additive Stochastic Uncertainty [19.229447330293546]
  Reinforcement learning (RL) methods often rely on massive exploration data to search optimal policies, and suffer from poor sampling efficiency. This paper presents a mixed RL algorithm by simultaneously using dual representations of environmental dynamics to search the optimal policy. The effectiveness of the mixed RL is demonstrated by a typical optimal control problem of non-affine nonlinear systems.
  arXiv  Detail & Related papers  (2020-02-28T08:02:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.