no code implementations • 7 Feb 2020 • Gilwoo Lee, Brian Hou, Sanjiban Choudhury, Siddhartha S. Srinivasa
We first obtain an ensemble of experts, one for each latent MDP, and fuse their advice to compute a baseline policy.
no code implementations • ICCV 2019 • Gilwoo Lee, Zhiwei Deng, Shugao Ma, Takaaki Shiratori, Siddhartha S. Srinivasa, Yaser Sheikh
We present a 16. 2-million frame (50-hour) multimodal dataset of two-person face-to-face spontaneous conversations.
no code implementations • 14 Sep 2019 • Gilwoo Lee, Christoforos Mavrogiannis, Siddhartha S. Srinivasa
Our goal is to guide human users towards optimal task performance while keeping their cognitive load as low as possible.
no code implementations • 30 May 2019 • Liyiming Ke, Sanjiban Choudhury, Matt Barnes, Wen Sun, Gilwoo Lee, Siddhartha Srinivasa
We show that the state-of-the-art methods such as GAIL and behavior cloning, due to their choice of loss function, often incorrectly interpolate between such modes.
no code implementations • 6 Oct 2018 • Gilwoo Lee, Sanjiban Choudhury, Brian Hou, Siddhartha S. Srinivasa
We present the first PAC optimal algorithm for Bayes-Adaptive Markov Decision Processes (BAMDPs) in continuous state and action spaces, to the best of our knowledge.
no code implementations • ICLR 2019 • Gilwoo Lee, Brian Hou, Aditya Mandalika, Jeongseok Lee, Sanjiban Choudhury, Siddhartha S. Srinivasa
Addressing uncertainty is critical for autonomous systems to robustly adapt to the real world.