English
Related papers

Related papers: Update-Free On-Policy Steering via Verifiers

200 papers

Improving the sample efficiency of reinforcement learning algorithms requires effective exploration. Following the principle of $\textit{optimism in the face of uncertainty}$ (OFU), we train a separate exploration policy to maximize the…

Machine Learning · Computer Science 2022-11-23 Jiachen Li , Shuo Cheng , Zhenyu Liao , Huayan Wang , William Yang Wang , Qinxun Bai

Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms…

Robots can acquire complex manipulation skills by learning policies from expert demonstrations, which is often known as vision-based imitation learning. Generating policies based on diffusion and flow matching models has been shown to be…

Robotics · Computer Science 2024-12-17 Qinglun Zhang , Zhen Liu , Haoqiang Fan , Guanghui Liu , Bing Zeng , Shuaicheng Liu

Building robotic agents capable of operating across diverse environments and object types remains a significant challenge, often requiring extensive data collection. This is particularly restrictive in robotics, where each data point must…

Robotics · Computer Science 2025-02-28 Siddhant Haldar , Lerrel Pinto

Learning from Observations (LfO) is a practical reinforcement learning scenario from which many applications can benefit through the reuse of incomplete resources. Compared to conventional imitation learning (IL), LfO is more challenging…

Machine Learning · Computer Science 2021-03-01 Zhuangdi Zhu , Kaixiang Lin , Bo Dai , Jiayu Zhou

Policy constraint methods in offline reinforcement learning employ additional regularization techniques to constrain the discrepancy between the learned policy and the offline dataset. However, these methods tend to result in overly…

Machine Learning · Computer Science 2024-08-06 Shirong Liu , Chenjia Bai , Zixian Guo , Hao Zhang , Gaurav Sharma , Yang Liu

Learning from expert demonstrations is a promising approach for training robotic manipulation policies from limited data. However, imitation learning algorithms require a number of design choices ranging from the input modality, training…

Robotics · Computer Science 2024-09-12 Eugenio Chisari , Nick Heppert , Max Argus , Tim Welschehold , Thomas Brox , Abhinav Valada

Behavioral Foundation Models (BFMs) proved successful in producing policies for arbitrary tasks in a zero-shot manner, requiring no test-time training or task-specific fine-tuning. Among the most promising BFMs are the ones that estimate…

Machine Learning · Computer Science 2026-05-05 Maksim Bobrin , Ilya Zisman , Alexander Nikulin , Vladislav Kurenkov , Dmitry Dylov

Learning-based methods for constructing control barrier functions (CBFs) are gaining popularity for ensuring safe robot control. A major limitation of existing methods is their reliance on extensive sampling over the state space or online…

Systems and Control · Electrical Eng. & Systems 2025-03-17 Hongzhan Yu , Seth Farrell , Ryo Yoshimitsu , Zhizhen Qin , Henrik I. Christensen , Sicun Gao

Achieving safe autonomous navigation systems is critical for deploying robots in dynamic and uncertain real-world environments. In this paper, we propose a hierarchical control framework leveraging neural network verification techniques to…

Artificial Intelligence · Computer Science 2025-05-01 Luca Marzari , Francesco Trotti , Enrico Marchesini , Alessandro Farinelli

Model-based reinforcement learning algorithms tend to achieve higher sample efficiency than model-free methods. However, due to the inevitable errors of learned models, model-based methods struggle to achieve the same asymptotic performance…

Machine Learning · Computer Science 2019-12-02 Qi Zhou , Houqiang Li , Jie Wang

Why do pretrained diffusion or flow-matching policies fail when the same task is performed near an obstacle, on a shifted support surface, or amid mild clutter? Such failures rarely reflect missing motor skills; instead, they expose a…

Robotics · Computer Science 2026-02-05 Shuo Liu , Ishneet Sukhvinder Singh , Yiqing Xu , Jiafei Duan , Ranjay Krishna

The Off-Policy Evaluation (OPE) problem consists of evaluating the performance of counterfactual policies with data collected by another one. To solve the OPE problem, we resort to estimators, which aim to estimate in the most accurate way…

Machine Learning · Computer Science 2024-11-12 Nicolò Felicioni , Michael Benigni , Maurizio Ferrari Dacrema

Behavioral Cloning (BC) aims at learning a policy that mimics the behavior demonstrated by an expert. The current theoretical understanding of BC is limited to the case of finite actions. In this paper, we study BC with the goal of…

Machine Learning · Computer Science 2022-12-09 Davide Maran , Alberto Maria Metelli , Marcello Restelli

This paper investigates the control barrier function (CBF) based safety-critical control for continuous nonlinear control affine systems using the more efficient online algorithms through time-varying optimization. The idea lies in that…

Systems and Control · Electrical Eng. & Systems 2023-03-21 Shengbo Wang , Shiping Wen , Yin Yang , Yuting Cao , Kaibo Shi , Tingwen Huang

Supervised imitation learning, also known as behavioral cloning, suffers from distribution drift leading to failures during policy execution. One approach to mitigate this issue is to allow an expert to correct the agent's actions during…

Robotics · Computer Science 2023-12-11 Trevor Ablett , Filip Marić , Jonathan Kelly

Despite strong multi-task pretraining, existing policies often exhibit poor task steerability. For example, a robot may fail to respond to a new instruction ``put the bowl in the sink" when moving towards the oven, executing ``close the…

Robotic foundation models, or generalist robot policies, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their advancements, our empirical experiments reveal that existing robot policies are…

Robotics · Computer Science 2026-04-27 Shihan Wu , Xu Luo , Ji Zhang , Junlin Xie , Jingkuan Song , Heng Tao Shen , Lianli Gao

Off-policy evaluation (OPE) holds the promise of being able to leverage large, offline datasets for both evaluating and selecting complex policies for decision making. The ability to learn offline is particularly important in many…

While imitation learning provides a simple and effective framework for policy learning, acquiring consistent actions during robot execution remains a challenging task. Existing approaches primarily focus on either modifying the action…

Robotics · Computer Science 2024-07-24 Xiao Liu , Fabian Weigend , Yifan Zhou , Heni Ben Amor
‹ Prev 1 3 4 5 6 7 10 Next ›