English
Related papers

Related papers: PPGuide: Steering Diffusion Policies with Performa…

200 papers

Deploying large, complex policies in the real world requires the ability to steer them to fit the needs of a situation. Most common steering approaches, like goal-conditioning, require training the robot policy with a distribution of…

Robotics · Computer Science 2025-11-11 Maximilian Du , Shuran Song

In many real-world settings, agents must learn from an offline dataset gathered by some prior behavior policy. Such a setting naturally leads to distribution shift between the behavior policy and the target policy being trained - requiring…

Machine Learning · Computer Science 2024-04-10 Matthew Thomas Jackson , Michael Tryfan Matthews , Cong Lu , Benjamin Ellis , Shimon Whiteson , Jakob Foerster

Diffusion models have recently gained prominence in offline reinforcement learning due to their ability to effectively learn high-performing, generalizable policies from static datasets. Diffusion-based planners facilitate long-horizon…

Machine Learning · Computer Science 2025-10-27 Donghyeon Ki , JunHyeok Oh , Seong-Woong Shim , Byung-Jun Lee

Recent works have shown the promise of inference-time search over action samples for improving generative robot policies. In particular, optimizing cross-chunk coherence via bidirectional decoding has proven effective in boosting the…

Robotics · Computer Science 2025-08-19 Rhea Malhotra , Yuejiang Liu , Chelsea Finn

Diffusion models have become popular for policy learning in robotics due to their ability to capture high-dimensional and multimodal distributions. However, diffusion policies are stochastic and typically trained offline, limiting their…

Robotics · Computer Science 2025-05-28 Ralf Römer , Alexander von Rohr , Angela P. Schoellig

We introduce Policy Gradient Guidance (PGG), a simple extension of classifier-free guidance from diffusion models to classical policy gradient methods. PGG augments the policy gradient with an unconditional branch and interpolates…

Machine Learning · Computer Science 2025-10-03 Jianing Qi , Hao Tang , Zhigang Zhu

Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidance for adapting a pre-trained diffusion model towards…

Machine Learning · Statistics 2024-10-17 Yingqing Guo , Hui Yuan , Yukang Yang , Minshuo Chen , Mengdi Wang

Diffusion Policy (DP) enables robots to learn complex behaviors by imitating expert demonstrations through action diffusion. However, in practical applications, hardware limitations often degrade data quality, while real-time constraints…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Jiahua Ma , Yiran Qin , Yixiong Li , Xuanqi Liao , Yulan Guo , Ruimao Zhang

Diffusion models have shown promise in forecasting future data from multivariate time series. However, few existing methods account for recurring structures, or patterns, that appear within the data. We present Pattern-Guided Diffusion…

Machine Learning · Computer Science 2025-12-17 Vivian Lin , Kuk Jin Jang , Wenwen Si , Insup Lee

Exploiting pre-trained diffusion models for restoration has recently become a favored alternative to the traditional task-specific training approach. Previous works have achieved noteworthy success by limiting the solution space using…

Computer Vision and Pattern Recognition · Computer Science 2023-09-20 Peiqing Yang , Shangchen Zhou , Qingyi Tao , Chen Change Loy

Diffusion models are generative models that have shown significant advantages compared to other generative models in terms of higher generation quality and more stable training. However, the computational need for training diffusion models…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Gulcin Baykal , Halil Faruk Karagoz , Taha Binhuraib , Gozde Unal

This paper introduces Diffusion Policy, a new way of generating robot behavior by representing a robot's visuomotor policy as a conditional denoising diffusion process. We benchmark Diffusion Policy across 12 different tasks from 4…

Robotics · Computer Science 2024-03-15 Cheng Chi , Zhenjia Xu , Siyuan Feng , Eric Cousineau , Yilun Du , Benjamin Burchfiel , Russ Tedrake , Shuran Song

The use of guidance to steer sampling toward desired outcomes has been widely explored within diffusion models, especially in applications such as image and trajectory generation. However, incorporating guidance during training remains…

Machine Learning · Computer Science 2025-05-21 Marvin Alles , Nutan Chen , Patrick van der Smagt , Botond Cseke

Recent advancements in diffusion models have revolutionized generative modeling. However, the impressive and vivid outputs they produce often come at the cost of significant model scaling and increased computational demands. Consequently,…

Machine Learning · Computer Science 2025-04-03 Jincheng Zhong , Xiangcheng Zhang , Jianmin Wang , Mingsheng Long

We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative strategies combat catastrophic forgetting by randomly sampling rehearsal examples from…

Machine Learning · Computer Science 2024-06-03 Bartosz Cywiński , Kamil Deja , Tomasz Trzciński , Bartłomiej Twardowski , Łukasz Kuciński

Recent developments in offline reinforcement learning have uncovered the immense potential of diffusion modeling, which excels at representing heterogeneous behavior policies. However, sampling from diffusion policies is considerably slow…

Machine Learning · Computer Science 2024-03-18 Huayu Chen , Cheng Lu , Zhengyi Wang , Hang Su , Jun Zhu

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…

Machine Learning · Computer Science 2025-05-30 Kevin Frans , Seohong Park , Pieter Abbeel , Sergey Levine

Route planning for navigation under partial observability plays a crucial role in modern robotics and autonomous driving. Existing route planning approaches can be categorized into two main classes: traditional autoregressive and…

Robotics · Computer Science 2024-04-04 Gengyu Zhang , Hao Tang , Yan Yan

Diffusion-based models for robotic control, including vision-language-action (VLA) and vision-action (VA) policies, have demonstrated significant capabilities. Yet their advancement is constrained by the high cost of acquiring large-scale…

Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or neuroscience, increasingly leveraging modern generative methods like diffusion models to map…

‹ Prev 1 2 3 10 Next ›