# Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning

arXiv: https://arxiv.org/abs/2407.20109 · HTML: https://mlsanity.com/paper/2407.20109/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 51 of its 58 references that are in the map.
- First posted on arXiv 29 Jul 2024.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- 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 51)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [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)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (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)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies](https://mlsanity.com/paper/2304.10573/) (2023)
- [Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble](https://mlsanity.com/paper/2110.01548/) (2021)
- [Critic Regularized Regression](https://mlsanity.com/paper/2006.15134/) (2020)
- [DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections](https://mlsanity.com/paper/1906.04733/) (2019)
- [MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale](https://mlsanity.com/paper/2104.08212/) (2021)
- [IQ-Learn: Inverse soft-Q Learning for Imitation](https://mlsanity.com/paper/2106.12142/) (2021)
- [AlgaeDICE: Policy Gradient from Arbitrary Experience](https://mlsanity.com/paper/1912.02074/) (2019)

## Built on by (most cited first, 30 of 42)

- [Flow Q-Learning](https://mlsanity.com/paper/2502.02538/) (2025)
- [Steering Your Diffusion Policy with Latent Space Reinforcement Learning](https://mlsanity.com/paper/2506.15799/) (2025)
- [DIME:Diffusion-Based Maximum Entropy Reinforcement Learning](https://mlsanity.com/paper/2502.02316/) (2025)
- [Diffusion Guidance Is a Controllable Policy Improvement Operator](https://mlsanity.com/paper/2505.23458/) (2025)
- [Flow-Based Policy for Online Reinforcement Learning](https://mlsanity.com/paper/2506.12811/) (2025)
- [Maximum Entropy Reinforcement Learning with Diffusion Policy](https://mlsanity.com/paper/2502.11612/) (2025)
- [Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning](https://mlsanity.com/paper/2502.04778/) (2025)
- [Prior-Guided Diffusion Planning for Offline Reinforcement Learning](https://mlsanity.com/paper/2505.10881/) (2025)
- [Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control](https://mlsanity.com/paper/2502.12724/) (2025)
- [Spatial-Temporal Aware Visuomotor Diffusion Policy Learning](https://mlsanity.com/paper/2507.06710/) (2025)
- [Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning](https://mlsanity.com/paper/2512.03973/) (2025)
- [Towards Robust Zero-Shot Reinforcement Learning](https://mlsanity.com/paper/2510.15382/) (2025)
- [Reinforcement Learning via Value Gradient Flow](https://mlsanity.com/paper/2604.14265/) (2026)
- [Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching](https://mlsanity.com/paper/2606.22630/) (2026)
- [Data Center Cooling System Optimization Using Offline Reinforcement Learning](https://mlsanity.com/paper/2501.15085/) (2025)
- [An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning](https://mlsanity.com/paper/2504.13368/) (2025)
- [Offline Multi-agent Reinforcement Learning via Sequential Score Decomposition](https://mlsanity.com/paper/2505.05968/) (2025)
- [Modular Diffusion Policy Training: Decoupling and Recombining Guidance and Diffusion for Offline RL](https://mlsanity.com/paper/2506.03154/) (2025)
- [FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies](https://mlsanity.com/paper/2603.27450/) (2026)
- [Mean Flow Policy Optimization](https://mlsanity.com/paper/2604.14698/) (2026)
- [Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning](https://mlsanity.com/paper/2505.01822/) (2025)
- [STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation](https://mlsanity.com/paper/2505.20781/) (2025)
- [Zero-Shot Off-Policy Learning](https://mlsanity.com/paper/2602.01962/) (2026)
- [Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning](https://mlsanity.com/paper/2605.01663/) (2026)
- [Trust-Region Diffusion Policies for Massively Parallel On-Policy RL](https://mlsanity.com/paper/2606.15260/) (2026)
- [Diffusion Self-Weighted Guidance for Offline Reinforcement Learning](https://mlsanity.com/paper/2505.18345/) (2025)
- [Semi-gradient DICE for Offline Constrained Reinforcement Learning](https://mlsanity.com/paper/2506.08644/) (2025)
- [Iterative Refinement of Flow Policies in Probability Space for Online Reinforcement Learning](https://mlsanity.com/paper/2510.15388/) (2025)
- [CAPE: Context-Aware Diffusion Policy Via Proximal Mode Expansion for Collision Avoidance](https://mlsanity.com/paper/2511.22773/) (2025)
- [Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations](https://mlsanity.com/paper/2601.01003/) (2026)

## Abstract (arXiv)

One important property of DIstribution Correction Estimation (DICE) methods is that the solution is the optimal stationary distribution ratio between the optimized and data collection policy. In this work, we show that DICE-based methods can be viewed as a transformation from the behavior distribution to the optimal policy distribution. Based on this, we propose a novel approach, Diffusion-DICE, that directly performs this transformation using diffusion models. We find that the optimal policy's score function can be decomposed into two terms: the behavior policy's score function and the gradient of a guidance term which depends on the optimal distribution ratio. The first term can be obtained from a diffusion model trained on the dataset and we propose an in-sample learning objective to learn the second term. Due to the multi-modality contained in the optimal policy distribution, the transformation in Diffusion-DICE may guide towards those local-optimal modes. We thus generate a few candidate actions and carefully select from them to approach global-optimum. Different from all other diffusion-based offline RL methods, the guide-then-select paradigm in Diffusion-DICE only uses in-sample actions for training and brings minimal error exploitation in the value function. We use a didatic toycase example to show how previous diffusion-based methods fail to generate optimal actions due to leveraging these errors and how Diffusion-DICE successfully avoids that. We then conduct extensive experiments on benchmark datasets to show the strong performance of Diffusion-DICE. Project page at https://ryanxhr.github.io/Diffusion-DICE/.