Haitao Xu, (former) PhD Student

Interests: Reinforcement Learning, Support Vector Machines, Deep Learning, Learning Theory, Surprise-Driven Learning

Haitao's Publications

H. Xu, L. Szymanski and B. McCane. VASE: Variational Assorted Surprise Exploration for Reinforcement Learning. IEEE Transactions on Neural Networks and Learning Systems, 34(3):1243-1252, 2023. Copy bibtex to clipboard
Bibtex has been copied to clipboard.
H. Xu. Intrinsic reward driven exploration for deep reinforcement learning. PhD thesis, University of Otago, 2021. Copy bibtex to clipboard
Bibtex has been copied to clipboard.
H. Xu, B. McCane, L. Szymanski and C. Atkinson. MIME: Mutual Information Minimisation Exploration. arXiv preprint arXiv:2001.05636, 2020. Copy bibtex to clipboard
Bibtex has been copied to clipboard.
H. Xu, B. McCane and L. Szymanski. Twin Bounded Large Margin Distribution Machine. In Australasian Joint Conference on Artificial Intelligence, pp. 718-729, 2018. Copy bibtex to clipboard
Bibtex has been copied to clipboard.
More of Haitao's publications can be found here.