English
Related papers

Related papers: Stochastic MeanFlow Policies: One-Step Generative …

200 papers

The ability to discover approximately optimal policies in domains with sparse rewards is crucial to applying reinforcement learning (RL) in many real-world scenarios. Approaches such as neural density models and continuous exploration…

Machine Learning · Computer Science 2019-09-25 Bogdan Mazoure , Thang Doan , Audrey Durand , R Devon Hjelm , Joelle Pineau

We present a comprehensive comparative study of three generative modeling paradigms: Denoising Diffusion Probabilistic Models (DDPM), Conditional Flow Matching (CFM), and MeanFlow. While DDPM and CFM require iterative sampling, MeanFlow…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Umang Agarwal , Rudraksh Sangore , Sumit Laddha

Generative models have emerged as a promising paradigm for offline multi-agent reinforcement learning (MARL), but existing approaches require many iterative sampling steps. Recent few-step acceleration methods either distill a joint teacher…

Artificial Intelligence · Computer Science 2026-05-14 Guowei Zou , Haitao Wang , Beiwen Zhang , Boning Zhang , Hejun Wu

Flow-based Generative Models (FGMs) effectively transform noise into complex data distributions. Incorporating Optimal Transport (OT) to couple noise and data during FGM training has been shown to improve the straightness of flow…

Machine Learning · Computer Science 2025-10-20 Lingkai Kong , Molei Tao , Yang Liu , Bryan Wang , Jinmiao Fu , Chien-Chih Wang , Huidong Liu

In Reinforcement Learning (RL), regularization has emerged as a popular tool both in theory and practice, typically based either on an entropy bonus or a Kullback-Leibler divergence that constrains successive policies. In practice, these…

Machine Learning · Computer Science 2025-06-18 Alena Shilova , Alex Davey , Brahim Driss , Riad Akrour

Reinforcement learning for control over continuous spaces typically uses high-entropy stochastic policies, such as Gaussian distributions, for local exploration and estimating policy gradient to optimize performance. Many robotic control…

Machine Learning · Computer Science 2024-04-03 Ya-Chien Chang , Sicun Gao

This work revisits standard policy gradient methods used on restricted policy classes, which are known to get stuck in suboptimal critical points. We identify an important cause for this phenomenon to be that the policy gradient is itself…

Machine Learning · Computer Science 2026-05-12 Alex DeWeese , Guannan Qu

Generative Flow Networks (GFlowNets) are a family of generative models that learn to sample objects with probabilities proportional to a given reward function. The key concept behind GFlowNets is the use of two stochastic policies: a…

Machine Learning · Computer Science 2025-03-04 Timofei Gritsaev , Nikita Morozov , Sergey Samsonov , Daniil Tiapkin

We cast episodic Markov decision process (MDP) planning as Bayesian inference over policies. A policy is treated as the latent variable and is assigned an unnormalized probability of optimality that is monotone in its expected return,…

Machine Learning · Computer Science 2026-04-14 David Tolpin

When large language models are fine-tuned to generate persona- or tone-conditioned responses, their output diversity is severely limited--a failure we term Cross-Style Collapse. We trace this collapse to the cross-entropy objective, which…

Computation and Language · Computer Science 2026-05-28 Kerui Peng , Feifei Li , Xingyu Fan , Wenhui Que

Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong…

Machine Learning · Computer Science 2023-05-23 Germano Gabbianelli , Gergely Neu , Nneka Okolo , Matteo Papini

Reinforcement learning (RL) is a fundamental methodology in autonomous driving systems, where generative policies exhibit considerable potential by leveraging their ability to model complex distributions to enhance exploration. However,…

Machine Learning · Computer Science 2026-03-04 Tianze Zhu , Yinuo Wang , Wenjun Zou , Tianyi Zhang , Likun Wang , Letian Tao , Feihong Zhang , Yao Lyu , Shengbo Eben Li

Many reinforcement learning (RL) tasks have discrete action spaces, but most generative policy methods based on diffusion and flow matching are designed for continuous control. Meanwhile, generative policies usually rely heavily on offline…

Machine Learning · Computer Science 2026-05-13 Fairoz Nower Khan , Nabuat Zaman Nahim , Peizhong Ju

Diffusion Q-Learning (DQL) has established diffusion policies as a high-performing paradigm for offline reinforcement learning, but its reliance on multi-step denoising for action generation renders both training and inference slow and…

Machine Learning · Computer Science 2026-02-25 Thanh Nguyen , Chang D. Yoo

In this work, we present a new model-free and off-policy reinforcement learning (RL) algorithm, that is capable of finding a near-optimal policy with state-action observations from arbitrary behavior policies. Our algorithm, called the…

Optimization and Control · Mathematics 2025-07-21 Narim Jeong , Donghwan Lee , Niao He

Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow primarily focuses on class-to-image generation. However, an…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Chenxi Zhao , Chen Zhu , Xiaokun Feng , Aiming Hao , Jiashu Zhu , Jiachen Lei , Jiahong Wu , Xiangxiang Chu , Jufeng Yang

Flow matching has emerged as a powerful generative modeling approach with flexible choices of source distribution. While Gaussian distributions are commonly used, the potential for better alternatives in high-dimensional data generation…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Junho Lee , Kwanseok Kim , Joonseok Lee

In the field of online reinforcement learning (RL), traditional Gaussian policies and flow-based methods are often constrained by their unimodal expressiveness, complex gradient clipping, or stringent trust-region requirements. Moreover,…

Machine Learning · Computer Science 2026-04-21 Qi Zhang

We propose a new reinforcement learning (RL) formulation for training continuous-time score-based diffusion models for generative AI to generate samples that maximize reward functions while keeping the generated distributions close to the…

Machine Learning · Computer Science 2025-08-12 Xuefeng Gao , Jiale Zha , Xun Yu Zhou

This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simple Deterministic Policy Gradient works remarkably well as…

Machine Learning · Computer Science 2020-06-30 Rasool Fakoor , Pratik Chaudhari , Alexander J. Smola