English
Related papers

Related papers: Aligning Flow Map Policies with Optimal Q-Guidance

200 papers

Soft actor-critic (SAC) is a popular algorithm for max-entropy reinforcement learning. In practice, the energy-based policies in SAC are often approximated using simple policy classes for efficiency, sacrificing the expressiveness and…

Machine Learning · Computer Science 2026-01-01 Yuyang Zhang , Yang Hu , Bo Dai , Na Li

Many data-driven decision problems are formulated using a nominal distribution estimated from historical data, while performance is ultimately determined by a deployment distribution that may be shifted, context-dependent, partially…

Machine Learning · Computer Science 2026-04-07 Xiuyuan Cheng , Yunqin Zhu , Yao Xie

Diffusion policies trained via offline behavioral cloning have recently gained traction in robotic motion generation. While effective, these policies typically require a large number of trainable parameters. This model size affords powerful…

Robotics · Computer Science 2025-04-29 Xiatao Sun , Shuo Yang , Yinxing Chen , Francis Fan , Yiyan Liang , Daniel Rakita

The Generative Flow Network is a probabilistic framework where an agent learns a stochastic policy for object generation, such that the probability of generating an object is proportional to a given reward function. Its effectiveness has…

Machine Learning · Computer Science 2022-10-10 Ling Pan , Dinghuai Zhang , Aaron Courville , Longbo Huang , Yoshua Bengio

Off-policy reinforcement learning holds the promise of sample-efficient learning of decision-making policies by leveraging past experience. However, in the offline RL setting -- where a fixed collection of interactions are provided and no…

Machine Learning · Computer Science 2021-01-15 Seyed Kamyar Seyed Ghasemipour , Dale Schuurmans , Shixiang Shane Gu

Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the performance of RL…

Machine Learning · Computer Science 2024-12-17 Shutong Ding , Ke Hu , Zhenhao Zhang , Kan Ren , Weinan Zhang , Jingyi Yu , Jingya Wang , Ye Shi

Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and…

Machine Learning · Computer Science 2018-09-17 Isac Arnekvist , Danica Kragic , Johannes A. Stork

Unitary Synthesis, the decomposition of a unitary matrix into a sequence of quantum gates, is a fundamental challenge in quantum compilation. Prevailing reinforcement learning (RL) approaches are often hampered by sparse reward signals,…

Quantum Physics · Physics 2026-03-05 Inhoe Koo , Hyunho Cha , Jungwoo Lee

Generative flow networks utilize a flow-matching loss to learn a stochastic policy for generating objects from a sequence of actions, such that the probability of generating a pattern can be proportional to the corresponding given reward.…

Machine Learning · Computer Science 2025-09-26 Leo Maxime Brunswic , Haozhi Wang , Shuang Luo , Jianye Hao , Amir Rasouli , Yinchuan Li

Flow-matching-based policies have recently emerged as a promising approach for learning-based robot manipulation, offering significant acceleration in action sampling compared to diffusion-based policies. However, conventional flow-matching…

Robotics · Computer Science 2025-10-03 Xuanran Zhai , Qianyou Zhao , Qiaojun Yu , Ce Hao

Diffusion policies have shown promise in learning complex behaviors from demonstrations, particularly for tasks requiring precise control and long-term planning. However, they face challenges in robustness when encountering distribution…

Machine Learning · Computer Science 2025-02-24 Mingyang Sun , Pengxiang Ding , Weinan Zhang , Donglin Wang

Deep generative models (DGMs) have demonstrated great success across various domains, particularly in generating texts, images, and videos using models trained from offline data. Similarly, data-driven decision-making and robotic control…

Machine Learning · Computer Science 2024-05-28 Jiayu Chen , Bhargav Ganguly , Yang Xu , Yongsheng Mei , Tian Lan , Vaneet Aggarwal

Diffusion-based models have recently shown strong performance in trajectory planning, as they are capable of capturing diverse, multimodal distributions of complex behaviors. A key limitation of these models is their slow inference speed,…

Robotics · Computer Science 2026-03-24 Grayson Lee , Minh Bui , Shuzi Zhou , Yankai Li , Mo Chen , Ke Li

Generative policies based on diffusion and flow matching have become a dominant paradigm for visuomotor robotic control. We show that replacing the standard Gaussian source distribution with WarmPrior, a simple temporally grounded prior…

Machine Learning · Computer Science 2026-05-15 Sinjae Kang , Chanyoung Kim , Kaixin Wang , Li Zhao , Kimin Lee

Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling. In this work, we extend these advances to weight space learning by leveraging…

Machine Learning · Computer Science 2025-10-17 Daniel Saragih , Deyu Cao , Tejas Balaji

Classifier-free guidance is a key component for enhancing the performance of conditional generative models across diverse tasks. While it has previously demonstrated remarkable improvements for the sample quality, it has only been…

Machine Learning · Computer Science 2023-12-11 Qinqing Zheng , Matt Le , Neta Shaul , Yaron Lipman , Aditya Grover , Ricky T. Q. Chen

Expressive generative policies such as diffusion and flow models are appealing for MaxEnt online reinforcement learning because of their ability to model multimodal and highly non-Gaussian action distributions. However, training effective…

Machine Learning · Computer Science 2026-05-12 Ke He , Le He , Shunpu Tang , Yafei Wang , Lisheng Fan

We study computationally and statistically efficient reinforcement learning under the linear $Q^{\pi}$ realizability assumption, where any policy's $Q$-function is linear in a given state-action feature representation. Prior methods in this…

Machine Learning · Computer Science 2026-03-03 Yijing Ke , Zihan Zhang , Ruosong Wang

We propose Functional Flow Matching (FFM), a function-space generative model that generalizes the recently-introduced Flow Matching model to operate in infinite-dimensional spaces. Our approach works by first defining a path of probability…

Machine Learning · Computer Science 2023-12-07 Gavin Kerrigan , Giosue Migliorini , Padhraic Smyth

We propose a method for learning expressive energy-based policies for continuous states and actions, which has been feasible only in tabular domains before. We apply our method to learning maximum entropy policies, resulting into a new…

Machine Learning · Computer Science 2017-07-25 Tuomas Haarnoja , Haoran Tang , Pieter Abbeel , Sergey Levine