English
Related papers

Related papers: Can Euclidean Symmetry be Leveraged in Reinforceme…

200 papers

Learning for robot navigation presents a critical and challenging task. The scarcity and costliness of real-world datasets necessitate efficient learning approaches. In this letter, we exploit Euclidean symmetry in planning for 2D…

Robotics · Computer Science 2024-01-30 Linfeng Zhao , Hongyu Li , Taskin Padir , Huaizu Jiang , Lawson L. S. Wong

Euclidean deep learning is often inadequate for addressing real-world signals where the representation space is irregular and curved with complex topologies. Interpreting the geometric properties of such feature spaces has become paramount…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 Ramzan Basheer , Deepak Mishra

Symmetry is a fundamental aspect of many real-world robotic tasks. However, current deep reinforcement learning (DRL) approaches can seldom harness and exploit symmetry effectively. Often, the learned behaviors fail to achieve the desired…

Robotics · Computer Science 2024-03-08 Mayank Mittal , Nikita Rudin , Victor Klemm , Arthur Allshire , Marco Hutter

In reinforcement learning (RL), exploiting environmental symmetries can significantly enhance efficiency, robustness, and performance. However, ensuring that the deep RL policy and value networks are respectively equivariant and invariant…

Machine Learning · Computer Science 2024-12-31 Mirco Theile , Hongpeng Cao , Marco Caccamo , Alberto L. Sangiovanni-Vincentelli

We study how group symmetry helps improve data efficiency and generalization for end-to-end differentiable planning algorithms when symmetry appears in decision-making tasks. Motivated by equivariant convolution networks, we treat the path…

Machine Learning · Computer Science 2023-05-02 Linfeng Zhao , Xupeng Zhu , Lingzhi Kong , Robin Walters , Lawson L. S. Wong

Reinforcement learning (RL) algorithms for continuous control tasks require accurate sampling-based action selection. Many tasks, such as robotic manipulation, contain inherent problem symmetries. However, correctly incorporating symmetry…

Robotics · Computer Science 2024-12-18 Linfeng Zhao , Owen Howell , Xupeng Zhu , Jung Yeon Park , Zhewen Zhang , Robin Walters , Lawson L. S. Wong

Equivariant neural networks have shown great success in reinforcement learning, improving sample efficiency and generalization when there is symmetry in the task. However, in many problems, only approximate symmetry is present, which makes…

Machine Learning · Computer Science 2025-04-24 Jung Yeon Park , Sujay Bhatt , Sihan Zeng , Lawson L. S. Wong , Alec Koppel , Sumitra Ganesh , Robin Walters

Model generalization of the underlying dynamics is critical for achieving data efficiency when learning for robot control. This paper proposes a novel approach for learning dynamics leveraging the symmetry in the underlying robotic system,…

Robotics · Computer Science 2022-10-17 Jee-eun Lee , Jaemin Lee , Tirthankar Bandyopadhyay , Luis Sentis

We propose a metric learning framework for the construction of invariant geometric functions of planar curves for the Eucledian and Similarity group of transformations. We leverage on the representational power of convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2017-02-20 Gautam Pai , Aaron Wetzler , Ron Kimmel

In many real-world applications of regression, conditional probability estimation, and uncertainty quantification, exploiting symmetries rooted in physics or geometry can dramatically improve generalization and sample efficiency. While…

Machine Learning · Computer Science 2025-05-28 Daniel Ordoñez-Apraez , Vladimir Kostić , Alek Fröhlich , Vivien Brandt , Karim Lounici , Massimiliano Pontil

Sampling efficiency is critical for deploying visuomotor learning in real-world robotic manipulation. While task symmetry has emerged as a promising inductive bias to improve efficiency, most prior work is limited to isometric symmetries --…

Robotics · Computer Science 2025-08-18 Hongbin Lin , Juan Rojas , Kwok Wai Samuel Au

Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information of the robot's kinematics and dynamics morphology. The…

This survey (re)introduces reinforcement learning methods to economists. The curse of dimensionality limits how far exact dynamic programming can be effectively applied, forcing us to rely on suitably "small" problems or our ability to…

General Economics · Economics 2026-03-25 Pranjal Rawat

Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area…

Machine Learning · Computer Science 2018-10-17 Winfried Lötzsch

Recent advances in deep learning and Transformers have driven major breakthroughs in robotics by employing techniques such as imitation learning, reinforcement learning, and LLM-based multimodal perception and decision-making. However,…

This paper proposes a novel online motion planning approach to robot navigation based on nonlinear model predictive control. Common approaches rely on pure Euclidean optimization parameters. In robot navigation, however, state spaces often…

Robotics · Computer Science 2022-01-06 Christoph Rösmann , Artemi Makarow , Torsten Bertram

We consider the problem of optimal path planning in different homotopy classes in a given environment. Though important in robotics applications, path-planning with reasoning about homotopy classes of trajectories has typically focused on…

Robotics · Computer Science 2017-10-10 Subhrajit Bhattacharya , Robert Ghrist

Consider a reinforcement learning problem where an agent has access to a very large amount of information about the environment, but it can only take very few actions to accomplish its task and to maximize its reward. Evidently, the main…

Machine Learning · Computer Science 2023-01-26 Nikola Andrejic , Vitaly Vanchurin

In many robot motion planning problems, task objectives and physical constraints induce non-Euclidean geometry on the configuration space, yet many planners operate using Euclidean distances that ignore this structure. We address the…

Robotics · Computer Science 2026-05-15 Phone Thiha Kyaw , Jonathan Kelly

Mobile manipulation requires coordinated control of high-dimensional, bimanual robots. Imitation learning methods have been broadly used to solve these robotic tasks, yet typically ignore the bilateral morphological symmetry inherent in…

‹ Prev 1 2 3 10 Next ›