no code implementations • 8 Sep 2023 • David Yunis, Justin Jung, Falcon Dai, Matthew Walter
Exploration in sparse-reward reinforcement learning is difficult due to the requirement of long, coordinated sequences of actions in order to achieve any reward.
no code implementations • 23 Feb 2023 • Takuma Yoneda, Luzhe Sun, and Ge Yang, Bradly Stadie, Matthew Walter
Traditional approaches to shared autonomy rely on knowledge of the environment dynamics, a discrete space of user goals that is known a priori, or knowledge of the user's policy -- assumptions that are unrealistic in many domains.
no code implementations • 28 Jul 2022 • Vitor Guizilini, Igor Vasiljevic, Jiading Fang, Rares Ambrus, Greg Shakhnarovich, Matthew Walter, Adrien Gaidon
Modern 3D computer vision leverages learning to boost geometric reasoning, mapping image data to classical structures such as cost volumes or epipolar constraints to improve matching.
2 code implementations • 8 Jan 2021 • Takuma Yoneda, Charles Schaff, Takahiro Maeda, Matthew Walter
This report describes our winning submission to the Real Robot Challenge (https://real-robot-challenge. com/).
no code implementations • NeurIPS 2019 • Falcon Dai, Matthew Walter
By analyzing the change in the maximum expected hitting cost, this work presents a formal understanding of the effect of potential-based reward shaping on regret (and sample complexity) in the undiscounted average reward setting.
no code implementations • 29 Nov 2017 • Thomas Kollar, Stefanie Tellex, Matthew Walter, Albert Huang, Abraham Bachrach, Sachi Hemachandra, Emma Brunskill, Ashis Banerjee, Deb Roy, Seth Teller, Nicholas Roy
Symbolic models capture linguistic structure but have not scaled successfully to handle the diverse language produced by untrained users.