English
Related papers

Related papers: SERNF: Sample-Efficient Real-World Dexterous Polic…

200 papers

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

Scene flow estimation is an essential ingredient for a variety of real-world applications, especially for autonomous agents, such as self-driving cars and robots. While recent scene flow estimation approaches achieve a reasonable accuracy,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Yushan Zhang , Bastian Wandt , Maria Magnusson , Michael Felsberg

Many score-based active learning methods have been successfully applied to graph-structured data, aiming to reduce the number of labels and achieve better performance of graph neural networks based on predefined score functions. However,…

Machine Learning · Computer Science 2023-04-25 Yinchuan Li , Zhigang Li , Wenqian Li , Yunfeng Shao , Yan Zheng , Jianye Hao

Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations. For such imitation policies, errors away from the training samples are particularly critical. Even…

Machine Learning · Computer Science 2024-03-19 Kaustubh Sridhar , Souradeep Dutta , Dinesh Jayaraman , James Weimer , Insup Lee

Diffusion models have emerged as powerful tools for generative modeling, demonstrating exceptional capability in capturing target data distributions from large datasets. However, fine-tuning these massive models for specific downstream…

Machine Learning · Computer Science 2025-09-01 Yinbin Han , Meisam Razaviyayn , Renyuan Xu

Bayesian posterior inference is prevalent in various machine learning problems. Variational inference provides one way to approximate the posterior distribution, however its expressive power is limited and so is the accuracy of resulting…

Machine Learning · Computer Science 2018-07-11 Guoqing Zheng , Yiming Yang , Jaime Carbonell

Diffusion policies, widely adopted in decision-making scenarios such as robotics, gaming and autonomous driving, are capable of learning diverse skills from demonstration data due to their high representation power. However, the sub-optimal…

Machine Learning · Computer Science 2025-09-30 Ningyuan Yang , Jiaxuan Gao , Feng Gao , Yi Wu , Chao Yu

Normalizing flows model a complex target distribution in terms of a bijective transform operating on a simple base distribution. As such, they enable tractable computation of a number of important statistical quantities, particularly…

Machine Learning · Computer Science 2022-09-01 Chandramouli Shama Sastry , Andreas Lehrmann , Marcus Brubaker , Alexander Radovic

For reinforcement learning in the real world online exploration is expensive A common practice in robotic reinforcement learning is to incorporate additional data to improve sample efficiency Expert demonstration data is often crucial for…

Machine Learning · Computer Science 2026-05-12 Daniel Palenicek , Florian Vogt , Joe Watson , Ingmar Posner , Danica Kragic , Jan Peters

Normalizing Flows (NFs) are a classical family of likelihood-based methods that have received revived attention. Recent efforts such as TARFlow have shown that NFs are capable of achieving promising performance on image modeling tasks,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Tianrong Chen , Jiatao Gu , David Berthelot , Joshua Susskind , Shuangfei Zhai

Diffusion-based policies have recently shown strong results in robot manipulation, but their extension to multi-task scenarios is hindered by the high cost of scaling model size and demonstrations. We introduce Skill Mixture-of-Experts…

Robotics · Computer Science 2026-01-30 Ce Hao , Xuanran Zhai , Yaohua Liu , Harold Soh

Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not hold (e.g., minority-group examples). Recent studies have…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Aryan Yazdan Parast , Khawar Islam , Soyoun Won , Basim Azam , Naveed Akhtar

Diffusion policies are becoming mainstream in robotic manipulation but suffer from hard negative class imbalance due to uniform sampling and lack of sample difficulty awareness, leading to slow training convergence and frequent inference…

Robotics · Computer Science 2026-04-20 Xinglei Yu , Zhenyang Liu , Shufeng Nan , Simo Wu , Yanwei Fu

Learning dexterous manipulation from few-shot demonstrations is a significant yet challenging problem for advanced, human-like robotic systems. Dense distilled feature fields have addressed this challenge by distilling rich semantic…

Robotics · Computer Science 2025-03-07 Qian Feng , David S. Martinez Lema , Jianxiang Feng , Zhaopeng Chen , Alois Knoll

We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing $\alpha$-divergences,…

Machine Learning · Statistics 2017-03-09 Stefan Depeweg , José Miguel Hernández-Lobato , Finale Doshi-Velez , Steffen Udluft

Discrete diffusion models have recently gained significant attention due to their ability to process complex discrete structures for language modeling. However, fine-tuning these models with policy gradient methods, as is commonly done in…

Machine Learning · Statistics 2025-12-19 Oussama Zekri , Nicolas Boullé

Flow-based policies have recently emerged as a powerful tool in offline and offline-to-online reinforcement learning, capable of modeling the complex, multimodal behaviors found in pre-collected datasets. However, the full potential of…

Machine Learning · Computer Science 2025-09-30 Deshu Chen , Yuchen Liu , Zhijian Zhou , Chao Qu , Yuan Qi

Generative Flow Networks (GFlowNets) were developed to learn policies for efficiently sampling combinatorial candidates by interpreting their generative processes as trajectories in directed acyclic graphs. In the value-based training…

Machine Learning · Computer Science 2026-03-03 Puhua Niu , Shili Wu , Xiaoning Qian

Generative models such as diffusion and flow matching have become dominant paradigms for visuomotor policy learning, yet their reliance on iterative denoising incurs high inference latency incompatible with real-time robotic control. We…

Robotics · Computer Science 2026-05-18 Jiaqi Bai , Jindou Jia , Yuxuan Hu , Gen Li , Xiangyu Chen , Tuo An , Kuangji Zuo , Jianfei Yang

The development of safety validation methods is essential for the safe deployment and operation of Automated Driving Systems (ADSs). One of the goals of safety validation is to prospectively evaluate the risk of an ADS dealing with…

Robotics · Computer Science 2025-07-31 Erwin de Gelder , Maren Buermann , Olaf Op den Camp