English
Related papers

Related papers: Policy Gradient Guidance Enables Test Time Control

200 papers

Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies.…

Machine Learning · Computer Science 2020-05-26 Rui Zhao , Volker Tresp

We study the estimation of policy gradients for continuous-time systems with known dynamics. By reframing policy learning in continuous-time, we show that it is possible construct a more efficient and accurate gradient estimator. The…

Machine Learning · Computer Science 2021-06-25 Samuel Ainsworth , Kendall Lowrey , John Thickstun , Zaid Harchaoui , Siddhartha Srinivasa

We introduce Spectral Guidance, a framework for controlling diffusion models by leveraging the intrinsic geometry of the generative process. As data is progressively corrupted by noise, only a small number of features remain informative for…

Machine Learning · Computer Science 2026-05-29 Gabriel Moreira , Manuel Marques , João Paulo Costeira , Chenyan Xiong

We present Generative Predictive Control (GPC), an inference-time method for improving pretrained behavior-cloning policies without retraining. GPC augments a frozen diffusion policy at deployment with an action-conditioned world model…

Robotics · Computer Science 2026-03-13 Han Qi , Haocheng Yin , Aris Zhu , Yilun Du , Heng Yang

Goal-conditioned policies enable decision-making models to execute diverse behaviors based on specified goals, yet their downstream performance is often highly sensitive to the choice of instructions or prompts. To bypass the limitations of…

Artificial Intelligence · Computer Science 2026-05-04 Guangyu Zhao , Kewei Lian , Haoxuan Ru , Borong Zhang , Haowei Lin , Zhancun Mu , Haobo Fu , Qiang Fu , Shaofei Cai , Zihao Wang , Yitao Liang

Real-world control systems require policies that are not only high-performing but also interpretable and robust. A promising direction toward this goal is model-based control, which learns system dynamics and cost functions from historical…

Systems and Control · Electrical Eng. & Systems 2025-11-20 Yuexin Bian , Jie Feng , Yuanyuan Shi

Policy gradient (PG) methods are the backbone of many reinforcement learning algorithms due to their good performance in policy optimization problems. As a gradient-based approach, PG methods typically rely on knowledge of the system…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Bowen Song , Andrea Iannelli

We present the Generalized Policy Gradient (GPG) Theorem, specifically designed for Transformer-based policies. Notably, we demonstrate that both standard Policy Gradient Theorem and GRPO emerge as special cases within our GPG framework.…

Machine Learning · Computer Science 2025-12-12 Hangyu Mao , Guangting Dong , Zhicheng Dou

With the rapid development of text-to-vision generation diffusion models, classifier-free guidance has emerged as the most prevalent method for conditioning. However, this approach inherently requires twice as many steps for model…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Huixuan Zhang , Junzhe Zhang , Xiaojun Wan

Stabilizing a dynamical system is a fundamental problem that serves as a cornerstone for many complex tasks in the field of control systems. The problem becomes challenging when the system model is unknown. Among the Reinforcement Learning…

Systems and Control · Electrical Eng. & Systems 2026-01-30 Ankang Zhang , Ming Chi , Xiaoling Wang , Lintao Ye

In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free guidance (CFG) is the de facto choice in modern systems and achieves this by contrasting…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Ankit Yadav , Ta Duc Huy , Lingqiao Liu

Many continuous control tasks have bounded action spaces. When policy gradient methods are applied to such tasks, out-of-bound actions need to be clipped before execution, while policies are usually optimized as if the actions are not…

Machine Learning · Computer Science 2018-06-25 Yasuhiro Fujita , Shin-ichi Maeda

Classifier-Free Guidance (CFG) is an essential component of text-to-image diffusion models, and understanding and advancing its operational mechanisms remains a central focus of research. Existing approaches stem from divergent theoretical…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Kaibo Wang , Jianda Mao , Tong Wu , Yang Xiang

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates (or sums) across actions when…

Machine Learning · Statistics 2020-05-05 Kamil Ciosek , Shimon Whiteson

Diffusion models have emerged as a powerful framework for generative modeling, with guidance techniques playing a crucial role in enhancing sample quality. Despite their empirical success, a comprehensive theoretical understanding of the…

Machine Learning · Statistics 2025-05-05 Gen Li , Yuchen Jiao

Classifier-guided diffusion models generate conditional samples by augmenting the reverse-time score with the gradient of the log-probability predicted by a probabilistic classifier. In practice, this classifier is usually obtained by…

Machine Learning · Statistics 2026-02-06 Sharan Sahu , Arisina Banerjee , Yuchen Wu

Classifier-Free Guidance (CFG) has emerged as a central approach for enhancing semantic alignment in flow-based diffusion models. In this paper, we explore a unified framework called CFG-Ctrl, which reinterprets CFG as a control applied to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Hanyang Wang , Yiyang Liu , Jiawei Chi , Fangfu Liu , Ran Xue , Yueqi Duan

Classifier-guided diffusion models have emerged as a powerful approach for conditional image generation, but they suffer from overconfident predictions during early denoising steps, causing the guidance gradient to vanish. This paper…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Seyed Alireza Javid , Amirhossein Bagheri , Nuria González-Prelcic

Training-free conditional diffusion provides a flexible alternative to task-specific conditional model training, but existing samplers often allocate computation inefficiently: independent guided trajectories can vary widely in quality, and…

Machine Learning · Statistics 2026-05-06 Andreas Makris , Paul Fearnhead , Chris Nemeth

Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. However, Classifier-Free Guidance (CFG) and extrapolation-based methods are heuristic…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Parsa Esmati , Junha Hyung , Amirhossein Dadashzadeh , Jaegul Choo , Majid Mirmehdi