SiMPO: Measure Matching for Online Diffusion Reinforcement Learning

• URL: http://arxiv.org/abs/2603.10250v1
• Date: Tue, 10 Mar 2026 22:01:13 GMT
• Title: SiMPO: Measure Matching for Online Diffusion Reinforcement Learning
• Abstract summary: We introduce SiMPO, a simple and unified framework that generalizes reweighting scheme in diffusion RL with general monotonic functions.<n>SiMPO revisits diffusion RL via a two-stage measure matching lens.<n>We provide geometric interpretations to illustrate how negative reweighting actively repels the policy from suboptimal actions.
• Score: 52.46919717963149
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A commonly used family of RL algorithms for diffusion policies conducts softmax reweighting over the behavior policy, which usually induces an over-greedy policy and fails to leverage feedback from negative samples. In this work, we introduce Signed Measure Policy Optimization (SiMPO), a simple and unified framework that generalizes reweighting scheme in diffusion RL with general monotonic functions. SiMPO revisits diffusion RL via a two-stage measure matching lens. First, we construct a virtual target policy by $f$-divergence regularized policy optimization, where we can relax the non-negativity constraint to allow for a signed target measure. Second, we use this signed measure to guide diffusion or flow models through reweighted matching. This formulation offers two key advantages: a) it generalizes to arbitrary monotonically increasing weighting functions; and b) it provides a principled justification and practical guidance for negative reweighting. Furthermore, we provide geometric interpretations to illustrate how negative reweighting actively repels the policy from suboptimal actions. Extensive empirical evaluations demonstrate that SiMPO achieves superior performance by leveraging these flexible weighting schemes, and we provide practical guidelines for selecting reweighting methods tailored to the reward landscape.

Related papers

• One-Way Policy Optimization for Self-Evolving LLMs [63.8638342097375]
  Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling reasoning capabilities of Large Language Models (LLMs)<n>We propose One-Way Policy Optimization (OWPO), a method based on the principle of decoupling optimization direction from update magnitude.<n> Experimental results demonstrate that OWPO outperforms strong baselines, including DAPO, OPD, and MOPD.
  arXiv  Detail & Related papers  (2026-05-21T08:25:27Z)
• Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment [51.18269946911088]
  Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF)<n>We show that DPO and RLHF optimize fundamentally different objectives in such cases.<n>We introduce Constrained Preference Optimization (CPO), augmenting RLHF with constraints for provable alignment.<n>Our theoretical analysis establishes when DPOs' guarantees hold and provides solutions preserving simplicity with provable alignment.
  arXiv  Detail & Related papers  (2026-05-20T07:26:22Z)
• Flow Matching Policy with Entropy Regularization [16.47598359293598]
  Flow Matching Policy with Entropy Regularization (FMER) is an Ordinary Differential Equation (ODE)-based online RL framework.<n>FMER parameterizes the policy via flow matching and samples actions along a straight probability path, motivated by optimal transport.<n> Experiments on sparse multi-goal FrankaKitchen benchmarks demonstrate that FMER outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-18T13:00:20Z)
• Coverage Improvement and Fast Convergence of On-policy Preference Learning [67.36750525893514]
  Online on-policy preference learning algorithms for language model alignment can significantly outperform their offline counterparts.<n>We analyze how the sampling policy's coverage evolves throughout on-policy training.<n>We develop principled on-policy schemes for reward distillation in the general function class setting.
  arXiv  Detail & Related papers  (2026-01-13T10:46:06Z)
• Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO [19.5712961932773]
  We revisit direct preference optimization (DPO) and demonstrate that its loss theoretically admits a decomposed reformulation.<n>We introduce PRoximalized PReference Optimization (PRO), a unified method to align with diverse feeback types.
  arXiv  Detail & Related papers  (2025-05-29T10:23:22Z)
• Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning [22.333460316347264]
  We introduce BDPO, a principled behavior-regularized RL framework tailored for diffusion-based policies.<n>We develop an efficient two-time-scale actor-critic RL algorithm that produces the optimal policy while respecting the behavior constraint.
  arXiv  Detail & Related papers  (2025-02-07T09:30:35Z)
• Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning [19.533619091287676]
  We propose a novel preferred-action-optimized diffusion policy for offline reinforcement learning. In particular, an expressive conditional diffusion model is utilized to represent the diverse distribution of a behavior policy. Experiments demonstrate that the proposed method provides competitive or superior performance compared to previous state-of-the-art offline RL methods.
  arXiv  Detail & Related papers  (2024-05-29T03:19:59Z)
• 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 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)

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.