Hengshuai Yao
Hengshuai Yao
Sony AI
Adresă de e-mail confirmată pe ualberta.ca - Pagina de pornire
Citat de
Citat de
Explainable artificial intelligence for autonomous driving: A comprehensive overview and field guide for future research directions
S Atakishiyev, M Salameh, H Yao, R Goebel
arXiv preprint arXiv:2112.11561, 2021
Negative log likelihood ratio loss for deep neural network classification
H Yao, D Zhu, B Jiang, P Yu
Proceedings of the Future Technologies Conference (FTC) 2019: Volume 1, 276-282, 2020
Distributional Reinforcement Learning for Efficient Exploration
B Mavrin, S Zhang, H Yao, K Kong, Linglong, Wu, Y Yu
https://arxiv.org/abs/1905.06125, 2019
Discounted reinforcement learning is not an optimization problem
A Naik, R Shariff, N Yasui, H Yao, RS Sutton
arXiv preprint arXiv:1910.02140, 2019
Mapless navigation among dynamics with social-safety-awareness: a reinforcement learning approach from 2d laser scans
J Jin, NM Nguyen, N Sakib, D Graves, H Yao, M Jagersand
2020 IEEE international conference on robotics and automation (ICRA), 6979-6985, 2020
Provably convergent two-timescale off-policy actor-critic with function approximation
S Zhang, B Liu, H Yao, S Whiteson
International Conference on Machine Learning, 11204-11213, 2020
Weakly supervised few-shot object segmentation using co-attention with visual and semantic embeddings
M Siam, N Doraiswamy, BN Oreshkin, H Yao, M Jagersand
arXiv preprint arXiv:2001.09540, 2020
Breaking the deadly triad with a target network
S Zhang, H Yao, S Whiteson
International Conference on Machine Learning, 12621-12631, 2021
Universal Option Models
H Yao, C Szepesvari, R Sutton, S Bhatnagar, J Modayil
A multi-component framework for the analysis and design of explainable artificial intelligence
MY Kim, S Atakishiyev, HKB Babiker, N Farruque, R Goebel, OR Zaïane, ...
Machine Learning and Knowledge Extraction 3 (4), 900-921, 2021
Method of prediction of a state of an object in the environment using an action model of a neural network
H Yao, SM Nosrati, H Chen, P Yadmellat, Y Zhang
US Patent 10,997,491, 2021
Multi-step dyna planning for policy evaluation and control
H Yao, S Bhatnagar, D Diao
Advances in neural information processing systems 22, 2009
Quota: The quantile option architecture for reinforcement learning
S Zhang, H Yao
Proceedings of the AAAI conference on artificial intelligence 33 (01), 5797-5804, 2019
Ace: An actor ensemble algorithm for continuous control with tree search
S Zhang, H Yao
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 5789-5796, 2019
Pseudo-MDPs and Factored Linear Action Models
H Yao, C Szepesvari, BA Pires, X Zhang
Method of selection of an action for an object using a neural network
H Yao, H Chen, SM Nosrati, P Yadmellat, Y Zhang
US Patent 10,935,982, 2021
Approximate policy iteration with linear action models
H Yao, C Szepesvári
Proceedings of the AAAI Conference on Artificial Intelligence 26 (1), 1212-1218, 2012
Hill climbing on value estimates for search-control in Dyna
Y Pan, H Yao, A Farahmand, M White
arXiv preprint arXiv:1906.07791, 2019
Towards practical hierarchical reinforcement learning for multi-lane autonomous driving
MS Nosrati, EA Abolfathi, M Elmahgiubi, P Yadmellat, J Luo, Y Zhang, ...
Preconditioned temporal difference learning
H Yao, ZQ Liu
Proceedings of the 25th international conference on Machine learning, 1208-1215, 2008
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–20