# Diffusion Guidance Is a Controllable Policy Improvement Operator

arXiv: https://arxiv.org/abs/2505.23458 · HTML: https://mlsanity.com/paper/2505.23458/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for offline RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 68 of its 76 references that are in the map.
- First posted on arXiv 29 May 2025.

## Placed in

- Offline RL and imitation learning from data / [Diffusion and flow policies for offline RL](https://mlsanity.com/offlinerl/diffusion-and-flow-policies-for-offline-rl/)

## Builds on (most cited first, 30 of 68)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Building Normalizing Flows with Stochastic Interpolants](https://mlsanity.com/paper/2209.15571/) (2022)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning](https://mlsanity.com/paper/2208.06193/) (2022)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies](https://mlsanity.com/paper/2304.10573/) (2023)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble](https://mlsanity.com/paper/2110.01548/) (2021)
- [Flow Matching Guide and Code](https://mlsanity.com/paper/2412.06264/) (2024)

## Built on by (most cited first, 30 of 58)

- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [DiffusionNFT: Online Diffusion Reinforcement with Forward Process](https://mlsanity.com/paper/2509.16117/) (2025)
- [RISE: Self-Improving Robot Policy with Compositional World Model](https://mlsanity.com/paper/2602.11075/) (2026)
- [Q-learning with Adjoint Matching](https://mlsanity.com/paper/2601.14234/) (2026)
- [Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control](https://mlsanity.com/paper/2602.13193/) (2026)
- [Learn to Guide Your Diffusion Model](https://mlsanity.com/paper/2510.00815/) (2025)
- [Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning](https://mlsanity.com/paper/2506.10137/) (2025)
- [chi0: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies](https://mlsanity.com/paper/2602.09021/) (2026)
- [Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance](https://mlsanity.com/paper/2508.21016/) (2025)
- [From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning](https://mlsanity.com/paper/2603.10263/) (2026)
- [ViVa: A Video-Generative Value Model for Robot Reinforcement Learning](https://mlsanity.com/paper/2604.08168/) (2026)
- [ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training](https://mlsanity.com/paper/2602.12691/) (2026)
- [Dichotomous Diffusion Policy Optimization](https://mlsanity.com/paper/2601.00898/) (2025)
- [GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering](https://mlsanity.com/paper/2603.15616/) (2026)
- [Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy](https://mlsanity.com/paper/2605.13435/) (2026)
- [Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning](https://mlsanity.com/paper/2606.11087/) (2026)
- [Latent Reasoning in TRMs is Secretly a Policy Improvement Operator](https://mlsanity.com/paper/2511.16886/) (2025)
- [PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning](https://mlsanity.com/paper/2602.01156/) (2026)
- [IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2602.20715/) (2026)
- [Reinforcement Learning via Value Gradient Flow](https://mlsanity.com/paper/2604.14265/) (2026)
- [Improving Robotic Generalist Policies via Flow Reversal Steering](https://mlsanity.com/paper/2606.13675/) (2026)
- [RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy](https://mlsanity.com/paper/2607.27782/) (2026)
- [Value-Guidance MeanFlow for Offline Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2604.08174/) (2026)
- [QPILOTS: Efficient Test-Time Q-Steering for Flow Policies](https://mlsanity.com/paper/2606.14801/) (2026)
- [Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2609.34575/) (2026)
- [Diffusion Policy through Conditional Proximal Policy Optimization](https://mlsanity.com/paper/2603.04790/) (2026)
- [Latent Policy Steering through One-Step Flow Policies](https://mlsanity.com/paper/2603.05296/) (2026)
- [MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives](https://mlsanity.com/paper/2603.22364/) (2026)
- [Refining Compositional Diffusion for Reliable Long-Horizon Planning](https://mlsanity.com/paper/2605.03075/) (2026)
- [JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning](https://mlsanity.com/paper/2605.13013/) (2026)

## Abstract (arXiv)

At the core of reinforcement learning is the idea of learning beyond the performance in the data. However, scaling such systems has proven notoriously tricky. In contrast, techniques from generative modeling have proven remarkably scalable and are simple to train. In this work, we combine these strengths, by deriving a direct relation between policy improvement and guidance of diffusion models. The resulting framework, CFGRL, is trained with the simplicity of supervised learning, yet can further improve on the policies in the data. On offline RL tasks, we observe a reliable trend -- increased guidance weighting leads to increased performance. Of particular importance, CFGRL can operate without explicitly learning a value function, allowing us to generalize simple supervised methods (e.g., goal-conditioned behavioral cloning) to further prioritize optimality, gaining performance for "free" across the board.