English
Related papers

Related papers: Truncated Rectified Flow Policy for Reinforcement …

200 papers

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

Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative…

Machine Learning · Computer Science 2026-05-22 Zeyuan Wang , Da Li , Yulin Chen , Yuehu Gong , Yanming Guo , Ye Shi , Liang Bai , Tianyuan Yu , Yanwei Fu

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

In reinforcement learning (RL), it is often advantageous to consider additional constraints on the action space to ensure safety or action relevance. Existing work on such action-constrained RL faces challenges regarding effective policy…

Machine Learning · Computer Science 2025-12-01 Roland Stolz , Michael Eichelbeck , Matthias Althoff

Entropy Regularisation is a widely adopted technique that enhances policy optimisation performance and stability. A notable form of entropy regularisation is augmenting the objective with an entropy term, thereby simultaneously optimising…

Machine Learning · Computer Science 2024-07-26 Jean Seong Bjorn Choe , Jong-Kook Kim

While behavior cloning with flow/diffusion policies excels at learning complex skills from demonstrations, it remains vulnerable to distributional shift, and standard RL methods struggle to fine-tune these models due to their iterative…

Machine Learning · Computer Science 2025-10-20 Mingyang Sun , Pengxiang Ding , Weinan Zhang , Donglin Wang

The Soft Actor-Critic (SAC) algorithm with a Gaussian policy has become a mainstream implementation for realizing the Maximum Entropy Reinforcement Learning (MaxEnt RL) objective, which incorporates entropy maximization to encourage…

Machine Learning · Computer Science 2025-06-09 Xiaoyi Dong , Jian Cheng , Xi Sheryl Zhang

Model-based reinforcement learning (MBRL) typically relies on modeling environment dynamics for data efficiency. However, due to the accumulation of model errors over long-horizon rollouts, such methods often face challenges in maintaining…

Machine Learning · Computer Science 2026-01-06 Bin Wang , Boxiang Tao , Haifeng Jing , Hongbo Dou , Zijian Wang

We consider the problem of sampling from a discrete and structured distribution as a sequential decision problem, where the objective is to find a stochastic policy such that objects are sampled at the end of this sequential process…

Machine Learning · Computer Science 2024-05-29 Tristan Deleu , Padideh Nouri , Nikolay Malkin , Doina Precup , Yoshua Bengio

Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution, which…

Machine Learning · Computer Science 2026-04-02 Ruijie Hao , Longfei Zhang , Yang Dai , Yang Ma , Xingxing Liang , Guangquan Cheng

This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions. We state a connection between sequential Monte Carlo (SMC) and neural sequential samplers…

Machine Learning · Computer Science 2025-10-14 Sanghyeok Choi , Sarthak Mittal , Víctor Elvira , Jinkyoo Park , Nikolay Malkin

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

Generative models such as diffusion and flow-matching offer expressive policies for offline reinforcement learning (RL) by capturing rich, multimodal action distributions, but their iterative sampling introduces high inference costs and…

Machine Learning · Computer Science 2026-02-26 Prajwal Koirala , Cody Fleming

Rectified Flow (RF) models have advanced high-quality image and video synthesis via optimal transport theory. However, when applied to image-to-image translation, they still depend on costly multi-step denoising, hindering real-time…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Shengqian Li , Ming Gao , Yi Liu , Zuzeng Lin , Feng Wang , Feng Dai

Generative flow and diffusion models provide the continuous, multimodal action distributions needed for high-precision robotic policies. However, their reliance on iterative sampling introduces severe inference latency, degrading control…

Robotics · Computer Science 2026-03-16 Shaolong Li , Lichao Sun , Yongchao Chen

Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their…

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality…

Machine Learning · Computer Science 2022-06-20 Zuxin Liu , Zhepeng Cen , Vladislav Isenbaev , Wei Liu , Zhiwei Steven Wu , Bo Li , Ding Zhao

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

Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling…

Machine Learning · Computer Science 2026-03-10 Guojian Zhan , Letian Tao , Pengcheng Wang , Yixiao Wang , Yiheng Li , Yuxin Chen , Hongyang Li , Masayoshi Tomizuka , Shengbo Eben Li

Real-world fine-tuning of dexterous manipulation policies remains challenging due to limited real-world interaction budgets and highly multimodal action distributions. Diffusion-based policies, while expressive, do not permit conservative…

Robotics · Computer Science 2026-04-07 Chenyu Yang , Denis Tarasov , Davide Liconti , Hehui Zheng , Robert K. Katzschmann
‹ Prev 1 2 3 10 Next ›