Zobrazeno 1 - 10
of 732
pro vyhledávání: '"Lawson, P S"'
Autor:
Bice, Tristan
We unify several extensions of the classic Stone duality due to Gr\"atzer, Hoffman-Lawson and Jung-S\"underhauf. Specifically we show that U-bases of locally compact sober spaces are dual to <-distributive v-predomains, where < is a transitive relati
Externí odkaz:
http://arxiv.org/abs/2002.09873
Autor:
Zhao, Linfeng, Howell, Owen, Zhu, Xupeng, Park, Jung Yeon, Zhang, Zhewen, Walters, Robin, Wong, Lawson L. S.
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 into sampli
Externí odkaz:
http://arxiv.org/abs/2412.12237
Autor:
Zhao, Linfeng, Wong, Lawson L. S.
Publikováno v:
Journal-ref: Reinforcement Learning Journal, Volume 5, 2024, Pages 2359-2372
Learning navigation capabilities in different environments has long been one of the major challenges in decision-making. In this work, we focus on zero-shot navigation ability using given abstract $2$-D top-down maps. Like human navigation by reading
Externí odkaz:
http://arxiv.org/abs/2412.12024
Autor:
Park, Jung Yeon, Bhatt, Sujay, Zeng, Sihan, Wong, Lawson L. S., Koppel, Alec, Ganesh, Sumitra, Walters, Robin
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 imposing e
Externí odkaz:
http://arxiv.org/abs/2411.04225
Autor:
Biza, Ondrej, Weng, Thomas, Sun, Lingfeng, Schmeckpeper, Karl, Kelestemur, Tarik, Ma, Yecheng Jason, Platt, Robert, van de Meent, Jan-Willem, Wong, Lawson L. S.
Reinforcement Learning (RL) has the potential to enable robots to learn from their own actions in the real world. Unfortunately, RL can be prohibitively expensive, in terms of on-robot runtime, due to inefficient exploration when learning from a spar
Externí odkaz:
http://arxiv.org/abs/2410.19989
Autor:
Pate, Seth, Wong, Lawson L. S.
We study the task of locating a user in a mapped indoor environment using natural language queries and images from the environment. Building on recent pretrained vision-language models, we learn a similarity score between text descriptions and images
Externí odkaz:
http://arxiv.org/abs/2410.03900
Data over non-Euclidean manifolds, often discretized as surface meshes, naturally arise in computer graphics and biological and physical systems. In particular, solutions to partial differential equations (PDEs) over manifolds depend critically on th
Externí odkaz:
http://arxiv.org/abs/2310.19589
Navigating in unseen environments is crucial for mobile robots. Enhancing them with the ability to follow instructions in natural language will further improve navigation efficiency in unseen cases. However, state-of-the-art (SOTA) vision-and-languag
Externí odkaz:
http://arxiv.org/abs/2310.10822
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 navigation, which o
Externí odkaz:
http://arxiv.org/abs/2309.13043
Autor:
Zhao, Linfeng, Howell, Owen, Park, Jung Yeon, Zhu, Xupeng, Walters, Robin, Wong, Lawson L. S.
In robotic tasks, changes in reference frames typically do not influence the underlying physical properties of the system, which has been known as invariance of physical laws.These changes, which preserve distance, encompass isometric transformations
Externí odkaz:
http://arxiv.org/abs/2307.08226