English
Related papers

Related papers: Entropy-Regularized Adjoint Matching for Offline R…

200 papers

We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm that tackles a long-standing challenge in continuous-action RL: efficient optimization of an expressive diffusion or flow-matching…

Machine Learning · Computer Science 2026-05-20 Qiyang Li , Sergey Levine

Diffusion policies are expressive yet incur high inference latency. Flow Matching (FM) enables one-step generation, but integrating it into Maximum Entropy Reinforcement Learning (MaxEnt RL) is challenging: the optimal policy is an…

Machine Learning · Computer Science 2026-02-03 Zeqiao Li , Yijing Wang , Haoyu Wang , Zheng Li , Zhiqiang Zuo

Generative policies based on expressive model classes, such as diffusion and flow matching, are well-suited to complex control problems with highly multimodal action distributions. Their expressivity, however, comes at a significant…

Machine Learning · Computer Science 2026-05-13 Christos Ziakas , Alessandra Russo , Avishek Joey Bose

Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Among reward-gradient-based methods, Adjoint Matching (AM) provides a principled…

Machine Learning · Computer Science 2026-05-19 Jeongwoo Shin , Dongsoo Shin , Yuchen Zhu , Wei Guo , Yongxin Chen , Joonseok Lee , Jaewoong Choi , Jaemoo Choi

Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL post-training aligns the model with a reward. In image…

Machine Learning · Computer Science 2026-05-19 Andreas Bergmeister , Stefanie Jegelka , Nikolas Nüsken , Carles Domingo-Enrich , Jakiw Pidstrigach

Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applicability remains largely confined to continuous action spaces. To address a broader range of…

Machine Learning · Computer Science 2026-05-14 Fairoz Nower Khan , Nabuat Zaman Nahim , Ruiquan Huang , Haibo Yang , Peizhong Ju

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

Maximum entropy reinforcement learning (MaxEnt-RL) has become the standard approach to RL due to its beneficial exploration properties. Traditionally, policies are parameterized using Gaussian distributions, which significantly limits their…

Machine Learning · Computer Science 2025-06-11 Onur Celik , Zechu Li , Denis Blessing , Ge Li , Daniel Palenicek , Jan Peters , Georgia Chalvatzaki , Gerhard Neumann

Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently, Q-learning with Adjoint Matching (QAM) addressed this issue by…

Machine Learning · Computer Science 2026-05-27 Yonghoon Dong , Kyungmin Lee , Changyeon Kim , Jaehyuk Kim , Jinwoo Shin

Computation methods for solving entropy-regularized reward optimization -- a class of problems widely used for fine-tuning generative models -- have advanced rapidly. Among those, Adjoint Matching (AM, Domingo-Enrich et al., 2025) has…

Machine Learning · Statistics 2026-02-17 Oswin So , Brian Karrer , Chuchu Fan , Ricky T. Q. Chen , Guan-Horng Liu

Offline reinforcement learning (RL) can fit strong value functions from fixed datasets, yet reliable deployment still hinges on the action selection interface used to query them. When the dataset induces a branched or multimodal action…

Machine Learning · Computer Science 2026-03-25 Haoyu Wang , Jingcheng Wang , Shunyu Wu , Xinwei Xiao

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

Entropy-based objectives are widely used to perform state space exploration in reinforcement learning (RL) and dataset generation for offline RL. Behavioral entropy (BE), a rigorous generalization of classical entropies that incorporates…

Machine Learning · Computer Science 2025-02-07 Wesley A. Suttle , Aamodh Suresh , Carlos Nieto-Granda

Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. However, despite its behavioral cloning expressiveness, FM-based…

Machine Learning · Computer Science 2025-10-14 Zhenglin Wan , Jingxuan Wu , Xingrui Yu , Chubin Zhang , Mingcong Lei , Bo An , Ivor Tsang

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

This paper investigates energy guidance in generative modeling, where the target distribution is defined as $q(\mathbf x) \propto p(\mathbf x)\exp(-\beta \mathcal E(\mathbf x))$, with $p(\mathbf x)$ being the data distribution and $\mathcal…

Machine Learning · Computer Science 2025-03-10 Shiyuan Zhang , Weitong Zhang , Quanquan Gu

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

Existing Maximum-Entropy (MaxEnt) Reinforcement Learning (RL) methods for continuous action spaces are typically formulated based on actor-critic frameworks and optimized through alternating steps of policy evaluation and policy…

Machine Learning · Computer Science 2024-10-29 Chen-Hao Chao , Chien Feng , Wei-Fang Sun , Cheng-Kuang Lee , Simon See , Chun-Yi Lee

Score-based and flow-based generative models exhibit remarkable expressive capacity in capturing complex distributions, and have been extensively deployed in tasks ranging from image generation to reinforcement learning. Nevertheless, these…

Machine Learning · Computer Science 2026-05-29 Yiyan , Liang , Sifei Liu , Weitong Zhang

With the increasing penetration of distributed energy resources, distributed optimization algorithms have attracted significant attention for power systems applications due to their potential for superior scalability, privacy, and…

Systems and Control · Electrical Eng. & Systems 2022-05-09 Sihan Zeng , Alyssa Kody , Youngdae Kim , Kibaek Kim , Daniel K. Molzahn
‹ Prev 1 2 3 10 Next ›