B
Byron Boots
Researcher at University of Washington
Publications - 227
Citations - 6473
Byron Boots is an academic researcher from University of Washington. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 35, co-authored 209 publications receiving 4801 citations. Previous affiliations of Byron Boots include Georgia Institute of Technology & Duke University.
Papers
More filters
Proceedings ArticleDOI
One-Shot Learning for Semantic Segmentation
TL;DR: In this paper, a network that, given a small set of annotated images, produces parameters for a Fully Convolutional Network (FCN) to perform dense pixel-level prediction on a test image for the new semantic class.
Proceedings ArticleDOI
Information theoretic MPC for model-based reinforcement learning
Grady Williams,Nolan Wagener,Brian Goldfain,Paul Drews,James M. Rehg,Byron Boots,Evangelos A. Theodorou +6 more
TL;DR: An information theoretic model predictive control algorithm capable of handling complex cost criteria and general nonlinear dynamics and using multi-layer neural networks as dynamics models to solve model-based reinforcement learning tasks is introduced.
Proceedings Article
Differentiable MPC for End-to-end Planning and Control
TL;DR: In this paper, the authors use model predictive control (MPC) to learn the cost and dynamics of a controller via end-to-end learning, and demonstrate that MPC policies are significantly more data-efficient than a generic neural network and that their method is superior to traditional system identification.
Proceedings Article
Hilbert Space Embeddings of Hidden Markov Models
TL;DR: This work proposes a nonparametric HMM that extends traditional HMMs to structured and non-Gaussian continuous distributions, and derives a local-minimum-free kernel spectral algorithm for learning these HMMs.
Proceedings ArticleDOI
Agile Autonomous Driving using End-to-End Deep Imitation Learning
Yunpeng Pan,Ching-An Cheng,Kamil Saigol,Keuntaek Lee,Xinyan Yan,Evangelos A. Theodorou,Byron Boots +6 more
TL;DR: In this article, an end-to-end imitation learning system for agile, off-road autonomous driving using only low-cost sensors is presented, where a deep neural network control policy is trained to map high-dimensional observations to continuous steering and throttle commands.