Sandy H Huang
Sandy H Huang
Research Scientist, DeepMind
Verified email at - Homepage
Cited by
Cited by
Adversarial attacks on neural network policies
S Huang, N Papernot, I Goodfellow, Y Duan, P Abbeel
arXiv preprint arXiv:1702.02284, 2017
Enabling robots to communicate their objectives
SH Huang, D Held, P Abbeel, AD Dragan
Robotics: Science and Systems (RSS), 2017
Expressing robot incapability
M Kwon, SH Huang, AD Dragan
Proceedings of the 2018 ACM/IEEE International Conference on Human-Robot …, 2018
Toward personalizing treatment for depression: predicting diagnosis and severity
SH Huang, P LePendu, SV Iyer, M Tai-Seale, D Carrell, NH Shah
Journal of the American Medical Informatics Association 21 (6), 1069-1075, 2014
Establishing appropriate trust via critical states
SH Huang, K Bhatia, P Abbeel, AD Dragan
2018 IEEE/RSJ international conference on intelligent robots and systems …, 2018
Attacking machine learning with adversarial examples
I Goodfellow, N Papernot, S Huang, Y Duan, P Abbeel, J Clark
OpenAI Blog 24, 1, 2017
A Distributional View on Multi-Objective Policy Optimization
A Abdolmaleki, SH Huang, L Hasenclever, M Neunert, HF Song, ...
International Conference on Machine Learning, 2020
Nifty: a system for large scale information flow tracking and clustering
C Suen, S Huang, C Eksombatchai, R Sosic, J Leskovec
Proceedings of the 22nd international conference on World Wide Web, 1237-1248, 2013
Learning agile soccer skills for a bipedal robot with deep reinforcement learning
T Haarnoja, B Moran, G Lever, SH Huang, D Tirumala, J Humplik, ...
Science Robotics 9 (89), eadi8022, 2024
Leveraging appearance priors in non-rigid registration, with application to manipulation of deformable objects
SH Huang, J Pan, G Mulcaire, P Abbeel
2015 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2015
Unifying scene registration and trajectory optimization for learning from demonstrations with application to manipulation of deformable objects
AX Lee, SH Huang, D Hadfield-Menell, E Tzeng, P Abbeel
2014 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2014
On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning
A Abdolmaleki, SH Huang, G Vezzani, B Shahriari, JT Springenberg, ...
arXiv preprint arXiv:2106.08199, 2021
Exploring exploration: Comparing children with rl agents in unified environments
E Kosoy, J Collins, DM Chan, S Huang, D Pathak, P Agrawal, J Canny, ...
arXiv preprint arXiv:2005.02880, 2020
Adversarial attacks on neural network policies. arXiv 2017
S Huang, N Papernot, I Goodfellow, Y Duan, P Abbeel
arXiv preprint arXiv:1702.02284, 0
A constrained multi-objective reinforcement learning framework
S Huang, A Abdolmaleki, G Vezzani, P Brakel, DJ Mankowitz, M Neunert, ...
Conference on Robot Learning, 883-893, 2022
Nonverbal robot feedback for human teachers
SH Huang, I Huang, R Pandya, AD Dragan
arXiv preprint arXiv:1911.02320, 2019
Human-AI learning performance in multi-armed bandits
R Pandya, SH Huang, D Hadfield-Menell, AD Dragan
Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 369-375, 2019
Beyond lowest-warping cost action selection in trajectory transfer
D Hadfield-Menell, AX Lee, C Finn, E Tzeng, S Huang, P Abbeel
2015 IEEE International Conference on Robotics and Automation (ICRA), 3231-3238, 2015
Towards understanding how machines can learn causal overhypotheses
E Kosoy, DM Chan, A Liu, J Collins, B Kaufmann, SH Huang, JB Hamrick, ...
arXiv preprint arXiv:2206.08353, 2022
Learning causal overhypotheses through exploration in children and computational models
E Kosoy, A Liu, JL Collins, D Chan, JB Hamrick, NR Ke, S Huang, ...
Conference on Causal Learning and Reasoning, 390-406, 2022
The system can't perform the operation now. Try again later.
Articles 1–20