English
Related papers

Related papers: Energy-Weighted Flow Matching for Offline Reinforc…

200 papers

Maximum likelihood (ML) learning for energy-based models (EBMs) is challenging, partly due to non-convergence of Markov chain Monte Carlo.Several variations of ML learning have been proposed, but existing methods all fail to achieve both…

Machine Learning · Statistics 2023-04-24 Xinwei Zhang , Zhiqiang Tan , Zhijian Ou

The task of conditional generation is one of the most important applications of generative models, and numerous methods have been developed to date based on the celebrated flow-based models. However, many flow-based models in use today are…

Machine Learning · Computer Science 2024-07-08 Noboru Isobe , Masanori Koyama , Jinzhe Zhang , Kohei Hayashi , Kenji Fukumizu

Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or…

Machine Learning · Computer Science 2024-05-31 Zeyu Fang , Tian Lan

Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions from offline data. These algorithms build on standard policy…

Machine Learning · Computer Science 2026-02-04 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

Dataset distillation compresses large datasets into compact synthetic sets with comparable performance in training models. Despite recent progress on diffusion-based distillation, this type of method typically depends on heuristic guidance…

Machine Learning · Computer Science 2026-02-06 Xuhui Li , Zhengquan Luo , Xiwei Liu , Yongqiang Yu , Zhiqiang Xu

Energy-based models (EBMs) are versatile density estimation models that directly parameterize an unnormalized log density. Although very flexible, EBMs lack a specified normalization constant of the model, making the likelihood of the model…

Machine Learning · Computer Science 2024-02-20 Louis Grenioux , Éric Moulines , Marylou Gabrié

We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for…

Machine Learning · Computer Science 2023-02-09 Yaron Lipman , Ricky T. Q. Chen , Heli Ben-Hamu , Maximilian Nickel , Matt Le

Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (RL). However, their iterative generative processes introduce substantial training and inference overhead. To overcome this…

Machine Learning · Computer Science 2026-04-17 Xiaoyi Dong , Xi Sheryl Zhang , Jian Cheng

Energy-based policies offer a flexible framework for modeling complex, multimodal behaviors in reinforcement learning (RL). In maximum entropy RL, the optimal policy is a Boltzmann distribution derived from the soft Q-function, but direct…

Machine Learning · Computer Science 2025-09-09 Vineet Jain , Tara Akhound-Sadegh , Siamak Ravanbakhsh

Flow-matching policies have emerged as a powerful paradigm for generalist robotics. These models are trained to imitate an action chunk, conditioned on sensor observations and textual instructions. Often, training demonstrations are…

Machine Learning · Computer Science 2025-07-22 Samuel Pfrommer , Yixiao Huang , Somayeh Sojoudi

Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to classical trajectory optimizers. While conceptually simple,…

Machine Learning · Computer Science 2022-12-22 Michael Janner , Yilun Du , Joshua B. Tenenbaum , Sergey Levine

Federated edge learning (FEEL) is a widely adopted framework for training an artificial intelligence (AI) model distributively at edge devices to leverage their data while preserving their data privacy. The execution of a power-hungry…

Information Theory · Computer Science 2021-02-25 Qunsong Zeng , Yuqing Du , Kaibin Huang

Off-dynamics offline reinforcement learning seeks to learn a target-domain policy from a large source dataset and a limited target dataset under mismatched transition dynamics. Existing approaches such as reward augmentation and data…

Machine Learning · Computer Science 2026-05-26 Yu Yang , Yihong Guo , Anqi Liu , Pan Xu

There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity. However, effectively leveraging this expressivity for value maximization remains…

Machine Learning · Computer Science 2026-05-14 JaeHyeok Doo , Byeongguk Jeon , Seonghyeon Ye , Kimin Lee , Minjoon Seo

Guidance techniques are commonly used in diffusion and flow models to improve image quality and input consistency for conditional generative tasks such as class-conditional and text-to-image generation. In particular, classifier-free…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Tariq Berrada Ifriqi , Adriana Romero-Soriano , Michal Drozdzal , Jakob Verbeek , Karteek Alahari

Model-based planning holds great promise for improving both sample efficiency and generalization in reinforcement learning (RL). We show that energy-based models (EBMs) are a promising class of models to use for model-based planning. EBMs…

Machine Learning · Computer Science 2021-03-09 Yilun Du , Toru Lin , Igor Mordatch

Despite remarkable progress in autoregressive language models, alternative generative paradigms beyond left-to-right generation are still being actively explored. Discrete diffusion models, with the capacity for parallel generation, have…

Computation and Language · Computer Science 2025-03-10 Minkai Xu , Tomas Geffner , Karsten Kreis , Weili Nie , Yilun Xu , Jure Leskovec , Stefano Ermon , Arash Vahdat

Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in the field of generative modeling due to its flexibility in the formulation and strong modeling power of the latent space. However,…

Machine Learning · Computer Science 2023-10-06 Peiyu Yu , Yaxuan Zhu , Sirui Xie , Xiaojian Ma , Ruiqi Gao , Song-Chun Zhu , Ying Nian Wu

We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL…

Machine Learning · Computer Science 2025-05-27 Seohong Park , Qiyang Li , Sergey Levine

Generative models have recently demonstrated remarkable success across diverse domains, motivating their adoption as expressive policies in reinforcement learning (RL). While they have shown strong performance in offline RL, particularly…

Machine Learning · Computer Science 2026-02-23 Yongjae Shin , Jongseong Chae , Jongeui Park , Youngchul Sung