# Diffusion Imitation from Observation

arXiv: https://arxiv.org/abs/2410.05429 · HTML: https://mlsanity.com/paper/2410.05429/

## Key facts

- Cited by 13 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 61 of its 84 references that are in the map.
- First posted on arXiv 7 Oct 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 / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 30 of 61)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [Imitating Human Behaviour with Diffusion Models](https://mlsanity.com/paper/2301.10677/) (2023)
- [Any-point Trajectory Modeling for Policy Learning](https://mlsanity.com/paper/2401.00025/) (2023)
- [Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning](https://mlsanity.com/paper/1809.02925/) (2018)
- [IQ-Learn: Inverse soft-Q Learning for Imitation](https://mlsanity.com/paper/2106.12142/) (2021)
- [LIV: Language-Image Representations and Rewards for Robotic Control](https://mlsanity.com/paper/2306.00958/) (2023)
- [Generative Adversarial Imitation from Observation](https://mlsanity.com/paper/1807.06158/) (2018)
- [Learning to Act from Actionless Videos through Dense Correspondences](https://mlsanity.com/paper/2310.08576/) (2023)

## Built on by (most cited first, 13 of 13)

- [Diffusing States and Matching Scores: A New Framework for Imitation Learning](https://mlsanity.com/paper/2410.13855/) (2024)
- [SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control](https://mlsanity.com/paper/2512.03028/) (2025)
- [Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation](https://mlsanity.com/paper/2501.14856/) (2025)
- [SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning](https://mlsanity.com/paper/2511.05355/) (2025)
- [Action-Constrained Imitation Learning](https://mlsanity.com/paper/2508.14379/) (2025)
- [On Generalization and Distributional Update for Mimicking Observations with Adequate Exploration](https://mlsanity.com/paper/2501.12785/) (2025)
- [CooT: Learning to Coordinate In-Context with Coordination Transformers](https://mlsanity.com/paper/2506.23549/) (2025)
- [Learning from Observation: A Survey of Recent Advances](https://mlsanity.com/paper/2509.19379/) (2025)
- [Latent Wasserstein Adversarial Imitation Learning](https://mlsanity.com/paper/2603.05440/) (2026)
- [Language-Critique Imitation Learning from Suboptimal Demonstrations](https://mlsanity.com/paper/2607.01225/) (2026)
- [Label-free Industrial Fault Detection via Adversarial Inverse Reinforcement Learning: A System for Run-to-Failure Prognostics](https://mlsanity.com/paper/2607.22987/) (2026)
- [Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching](https://mlsanity.com/paper/2609.38955/) (2026)
- [Beyond the End-Effector: Learning Whole-Arm Contact Manipulation from Human Demonstrations](https://mlsanity.com/paper/2610.17802/) (2026)

## Abstract (arXiv)

Learning from observation (LfO) aims to imitate experts by learning from state-only demonstrations without requiring action labels. Existing adversarial imitation learning approaches learn a generator agent policy to produce state transitions that are indistinguishable to a discriminator that learns to classify agent and expert state transitions. Despite its simplicity in formulation, these methods are often sensitive to hyperparameters and brittle to train. Motivated by the recent success of diffusion models in generative modeling, we propose to integrate a diffusion model into the adversarial imitation learning from observation framework. Specifically, we employ a diffusion model to capture expert and agent transitions by generating the next state, given the current state. Then, we reformulate the learning objective to train the diffusion model as a binary classifier and use it to provide "realness" rewards for policy learning. Our proposed framework, Diffusion Imitation from Observation (DIFO), demonstrates superior performance in various continuous control domains, including navigation, locomotion, manipulation, and games. Project page: https://nturobotlearninglab.github.io/DIFO