Tianyi Huang

A CNN-based policy for optimizing continuous action control by learning state sequences

William Zhu, Xiaolong Qin, Tianyi Huang, 2022, Neurocomputing.

Anchor: The achieved goal to replace the subgoal for hierarchical reinforcement learning

William Zhu, Zhiling Cai, Tianyi Huang, 2021, Knowl. Based Syst..

WDIBS: Wasserstein deterministic information bottleneck for state abstraction to balance state-compression and performance

Xianchao Zhu, William Zhu, Tianyi Huang, 2021, Applied Intelligence.

Adaptive exploration policy for exploration–exploitation tradeoff in continuous action control optimization

William Zhu, Tianyi Huang, Min Li, 2021, International Journal of Machine Learning and Cybernetics.