Recent Projects
This section includes a portfolio of my most recent projects. Take a moment to explore below, and go to Code if you’re interested in learning more about what I have to offer.
Towards Deep Reinforcement Learning Without Environment -- A Case Study on Aunomous Greenhouse Control
Research Engineer Intern, 2019
This project tries to apply recent advancement in RL and Deep Learning to agriculture. It tried the RL approach to learn a planting strategy to help the growth of cucumbers via remote greenhouse control.
I assisted Ph.D. candidate Lu Wang under Dr. Dijun Luo's supervision at the AI Lab in Tecent in China.
​
This work has been submitted to AAAI 2020 for review.
Adaptive Recommendation System: A Deep RL Approach
Undergraduate Thesis Project, 2019
This project tries to apply recent advancement in RL and Deep Learning to Recommendation Systems. It focuses on the model-based RL approach. This is also my undergraduate thesis project.
I work with Prof. Weinan Zhang and Xinyi Dai in the APEX Data and Knowledge Management Lab at Shanghai Jiao Tong University.
​
Find the thesis here.
Temporal Difference Learning with Emphasis
Research Intern, 2018
This project investigates the performance of on-policy Emphatic Temporal Difference (ETD) methods empirically.
I work with Sina Ghiassian under the supervision of Prof. Rich Sutton in the Reinforcement Learning and Artificial Intelligence (RLAI) lab at The University of Alberta.
Find the paper here .
(Pre-print on arXiv 1903.00194)
Adaptive Off-Policy Policy Gradient Methods
Research Intern, 2018
This project investigates how we can apply off-policy methods in control in RL in a more data-efficient way.
I work with Josiah P. Hanna under the supervision of Prof. Peter Stone in the Learning Agents Research Group at the University of Texas at Austin.
Find the draft report here!
Course Project, 2018
This is the course project of CS343--Artificial Intelligence given by Prof. Scott Niekum at the University of Texas at Austin.
It provides a graphical interface Pacman, developed by UCBerkeley, to let students implement some of the core algorithms in AI including search, multi-agents, RL, HMM, and Machine Learning, and allow students to visualize the results.
​
Find source code here!
Course Project, 2018
This is the course project of CS429--Computer Architecture given by Prof. Bill Young at the University of Texas at Austin.
It helps students gain a better and deeper understanding of the architecture of modern computers through a series of labs, where each lab touches a different aspect of computer architecture such as bit operation, assembly language, reverse engineering, computer attacking, pipelining, and caching.
Find source code here!
Course Project, 2017
This is the course project of CS337--Computer Graphics given by Prof. Sheng Bin at Shanghai Jiao Tong University.
It implements a novel method for simulating rainbows in computers proposed in this paper.
Great thanks to my teammates on this project: Yao Zhao and Jiannan Liu.
​
Find source code here!