English
Related papers

Related papers: Policy Gradient Guidance Enables Test Time Control

200 papers

Diffusion Policies (DPs) have attracted attention for their ability to achieve significant accuracy improvements in various imitation learning tasks. However, DPs depend on Diffusion Models, which require multiple noise removal steps to…

Machine Learning · Computer Science 2025-07-30 Sodtavilan Odonchimed , Tatsuya Matsushima , Simon Holk , Yusuke Iwasawa , Yutaka Matsuo

Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully…

Machine Learning · Computer Science 2020-05-26 Kamyar Azizzadenesheli , Yisong Yue , Animashree Anandkumar

Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking…

Diffusion models deliver high quality in image synthesis but remain expensive during training and inference. Recent works have leveraged the inherent redundancy in visual content to make training more affordable by training only on a subset…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Felix Krause , Stefan Andreas Baumann , Johannes Schusterbauer , Olga Grebenkova , Ming Gui , Vincent Tao Hu , Björn Ommer

The theory of continuous-time reinforcement learning (RL) has progressed rapidly in recent years. While the ultimate objective of RL is typically to learn deterministic control policies, most existing continuous-time RL methods rely on…

Machine Learning · Computer Science 2026-03-17 Ziheng Cheng , Xin Guo , Yufei Zhang

Projected policy gradient (PPG) is a basic policy optimization method in reinforcement learning. Given access to exact policy evaluations, previous studies have established the sublinear convergence of PPG for sufficiently small step sizes…

Optimization and Control · Mathematics 2024-09-19 Jiacai Liu , Wenye Li , Dachao Lin , Ke Wei , Zhihua Zhang

Diffusion models have shown tremendous results in image generation. However, due to the iterative nature of the diffusion process and its reliance on classifier-free guidance, inference times are slow. In this paper, we propose a new…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Yi-Ting Hsiao , Siavash Khodadadeh , Kevin Duarte , Wei-An Lin , Hui Qu , Mingi Kwon , Ratheesh Kalarot

Generative models, particularly diffusion models, have achieved remarkable success in density estimation for multimodal data, drawing significant interest from the reinforcement learning (RL) community, especially in policy modeling in…

Machine Learning · Computer Science 2024-12-03 Jinouwen Zhang , Rongkun Xue , Yazhe Niu , Yun Chen , Jing Yang , Hongsheng Li , Yu Liu

Classifier-Free Guidance (CFG) is a fundamental technique in training conditional diffusion models. The common practice for CFG-based training is to use a single network to learn both conditional and unconditional noise prediction, with a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Prin Phunyaphibarn , Phillip Y. Lee , Jaihoon Kim , Minhyuk Sung

This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simple Deterministic Policy Gradient works remarkably well as…

Machine Learning · Computer Science 2020-06-30 Rasool Fakoor , Pratik Chaudhari , Alexander J. Smola

In light of the widespread success of generative models, a significant amount of research has gone into speeding up their sampling time. However, generative models are often sampled multiple times to obtain a diverse set incurring a cost…

Machine Learning · Computer Science 2023-11-27 Gabriele Corso , Yilun Xu , Valentin de Bortoli , Regina Barzilay , Tommi Jaakkola

Classifier free guidance is a standard method for conditional sampling in diffusion models, but its sampling rule is not aligned with the objective used in training. This mismatch induces a structural sampling error through the interaction…

Machine Learning · Computer Science 2026-05-27 Nakgyu Yang , Yechan Lee , SooJean Han

Deep reinforcement learning (RL) algorithms typically parameterize the policy as a deep network that outputs either a deterministic action or a stochastic one modeled as a Gaussian distribution, hence restricting learning to a single…

Machine Learning · Computer Science 2024-06-04 Zechu Li , Rickmer Krohn , Tao Chen , Anurag Ajay , Pulkit Agrawal , Georgia Chalvatzaki

Standard policy gradients weight each sampled action by advantage alone, regardless of how likely that action was under the current policy. This creates two pathologies: within a single decision context (e.g. one image or prompt), a rare…

Machine Learning · Computer Science 2026-03-17 Ian Osband

Recent advances in diffusion models attempt to handle conditional generative tasks by utilizing a differentiable loss function for guidance without the need for additional training. While these methods achieved certain success, they often…

Machine Learning · Computer Science 2024-07-08 Lingxiao Yang , Shutong Ding , Yifan Cai , Jingyi Yu , Jingya Wang , Ye Shi

Deterministic policy gradient (DPG) is widely utilized for continuous control; however, it inherently relies on the differentiability of the critic with respect to the action during policy updates. This assumption is violated in practical…

Machine Learning · Computer Science 2026-05-08 Hyunjun Na , Donghwan Lee

Can a text-to-image diffusion model be used as a training objective for adapting a GAN generator to another domain? In this paper, we show that the classifier-free guidance can be leveraged as a critic and enable generators to distill…

Computer Vision and Pattern Recognition · Computer Science 2022-12-12 Kunpeng Song , Ligong Han , Bingchen Liu , Dimitris Metaxas , Ahmed Elgammal

In this paper, we revisit and improve the convergence of policy gradient (PG), natural PG (NPG) methods, and their variance-reduced variants, under general smooth policy parametrizations. More specifically, with the Fisher information…

Machine Learning · Computer Science 2022-11-17 Yanli Liu , Kaiqing Zhang , Tamer Başar , Wotao Yin

Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models. While they can be easily generated using gradient-based techniques in digital and physical…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Haotian Xue , Alexandre Araujo , Bin Hu , Yongxin Chen

Classifier-free guidance (CFG) is a core technique powering state-of-the-art image generation systems, yet its underlying mechanisms remain poorly understood. In this work, we begin by analyzing CFG in a simplified linear diffusion model,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Xiang Li , Rongrong Wang , Qing Qu
‹ Prev 1 4 5 6 7 8 10 Next ›