**Tzu-Yun Ariel Shann** ![](images/ariel.jpg width="256")
Education =================================================================== 2018-Present : *MSc Candidate in Computer Science* at *University of British Columbia* :
_Vancouver BC, Canada_ : - *Supervisor*: Leonid Sigal : - *Research interests*: deep reinforcement learning, computer vision 2014-2017 : *BSc in Computer Science* at *National Tsing Hua University* :
_Hsinchu, Taiwan_ Experience =================================================================== 2020/5-Present : *Research Intern* at *Borealis AI* :
_Toronro ON, Canada_ : - *Supervisor*: Ruitong Huang, Pablo Hernandez Leal : - *Research topic*: exploration strategies for reinforcement learning 2017/1-2018/8 : *Research Assistant* at *National Tsing Hua University* :
_Hsinchu, Taiwan_ : - *Supervisor*: [Chun-Yi Lee](http://cymaxwelllee.wixsite.com/elsa) : - *Research topic*: reinforcement learning, multi-agent reinforcement learning 2016/7-2016/9 : *Software Engineer Intern* at *MediaTek* :
_Hsinchu, Taiwan_ Publications =================================================================== + *Adversarial Exploration Strategy for Self-Supervised Imitation Learning*
Zhang-Wei Hong, Tsu-Jui Fu, *Tzu-Yun Shann*, Yi-Hsiang Chang, Chun-Yi Lee.
In Proceedings of the _Conference of Robot Learning (*CoRL*)_, Oct. 2019 (_Oral presentation_)
Paper + *Diversity-Driven Exploration Strategy for Deep Reinforcement Learning*
Zhang-Wei Hong, *Tzu-Yun Shann*, Shih-Yang Su, Yi-Hsiang Chang, Tsu-Jui Fu, Chun-Yi Lee.
In Advances in _Neural Information Processing Systems (*NeurIPS*)_, Dec. 2018.
(A [shorter version](https://openreview.net/pdf?id=BJsD7L1vz) of this paper has been accepted in ICLR 2018 Workshop)
Paper + *A Deep Policy Inference Q-Network for Multi-Agent Systems*
*Tzu-Yun Shann*♮, Shih-Yang Su♮, Zhang-Wei Hong♮, Yi-Hsiang Chang, Chun-Yi Lee.
In Proceedings of the _International Conference on Autonomous Agents and Multi-Agent Systems (*AAMAS*)_, Jul. 2018.
(♮ indicates equal contribution)
Paper Code + *Virtual-to-Real: Learning to Control in Visual Semantic Segmentation*
Zhang-Wei Hong, Yu-Min Chen, Shih-Yang Su, *Tzu-Yun Shann*, Yi-Hsiang Chang, Hsuan-Kung Yang, Brian Hsi-Lin Ho, Chih-Chieh Tu, Yueh-Chuan Chang, Tsu-Ching Hsiao, Hsin-Wei Hsiao, Sih-Pin Lai, Chun-Yi Lee.
In Proceedings of the _International Joint Conference on Artificial Intelligence (*IJCAI*)_, Jul. 2018.
Paper Video Teaching ================================================================== Winter I, 2018 : Teaching assistant for [CPSC425 Computer Vision](https://www.cs.ubc.ca/~lsigal/teaching18_Term1.html) Winter II, 2018 : Teaching assistant for [CPSC425 Computer Vision](https://www.cs.ubc.ca/~lsigal/teaching18_Term2.html) Winter I, 2019 : Teaching assistant for CPSC322 Introduction to Artificial Intelligence Dec 2019 : Teaching assistant for [IVADO/MILA/DSI Deep Learning School](https://ivado.ca/en/trainings/schools/ivado-mila-deep-learning-school-5th-edition-2/) Winter II, 2019 : Teaching assistant for [CPSC425 Computer Vision](https://www.cs.ubc.ca/~lsigal/teaching19_Term2.html) Service ================================================================= Reviewing ----------------------------------------------------------------- - *NeurIPS* 2019, 2020 - *ICML* 2020 Volunteering ----------------------------------------------------------------- - *NeurIPS* 2018 - *ICLR* 2020 - *ICML* 2020 !!! note: Misc - I was born and raised in *Taiwan*, a beautiful island in the Pacific. - Outside of work and research, I enjoy baking, cooking, drawing, bullet journaling, and playing the piano. - I love *traveling*. I have been to Japan, Indonesia, USA, UK, Italy, Germany, the Netherlands, Belgium, Austria, Canada, Sweden and France. I also know a bit of German and Spanish. - I am obsessed with *mechanical keyboards*:) - I am not a gamer, but I enjoy playing games on my Nintendo Switch once in a while. My current favourite games include Overcooked, Animal Crossing, and Ring Fit Adventures.