Search Results for author: Richard Cheng

Found 5 papers, 4 papers with code

Safe Multi-Agent Interaction through Robust Control Barrier Functions with Learned Uncertainties

1 code implementation11 Apr 2020 Richard Cheng, Mohammad Javad Khojasteh, Aaron D. Ames, Joel W. Burdick

Robots operating in real world settings must navigate and maintain safety while interacting with many heterogeneous agents and obstacles.


Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits

1 code implementation13 Mar 2020 Maegan Tucker, Myra Cheng, Ellen Novoseller, Richard Cheng, Yisong Yue, Joel W. Burdick, Aaron D. Ames

Optimizing lower-body exoskeleton walking gaits for user comfort requires understanding users' preferences over a high-dimensional gait parameter space.

Control Regularization for Reduced Variance Reinforcement Learning

1 code implementation14 May 2019 Richard Cheng, Abhinav Verma, Gabor Orosz, Swarat Chaudhuri, Yisong Yue, Joel W. Burdick

We show that functional regularization yields a bias-variance trade-off, and propose an adaptive tuning strategy to optimize this trade-off.

Continuous Control reinforcement-learning +1

End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks

1 code implementation21 Mar 2019 Richard Cheng, Gabor Orosz, Richard M. Murray, Joel W. Burdick

Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process.

Continuous Control Gaussian Processes +2

Cannot find the paper you are looking for? You can Submit a new open access paper.