Ryan Shi

I research, develop, deploy, and evaluate AI for social good. [CV]

Fei Fang makes this unworldly dream possible. I also work with Rayid Ghani and Steven Wu.

My technical research lies in data science, game theory, and reinforcement learning.

Contact: ryanshi[attt]cmu[dott]edu.

AI is easy, social good is hard. The former is shown below, the latter is a lifetime goal.

Artificial Intelligence for Social Good: A Survey
Zheyuan Ryan Shi, Claire Wang, Fei Fang
Working paper, 2020.
[Abstract][Initial version][2020 Symposium on AI and Social Good @CMU]

Bandit Data-driven Optimization: AI for Social Good and Beyond
Zheyuan Ryan Shi, Zhiwei Steven Wu, Rayid Ghani, Fei Fang
Working paper, 2020.
[Abstract][Initial version]

Improving Efficiency of Volunteer-Based Food Rescue Operations
Zheyuan Ryan Shi, Yiwen Yuan, Kimberly Lo, Leah Lizarondo, Fei Fang
IAAI-20: 32nd Annual Conference on Innovative Applications of Artificial Intelligence
[Abstract][IAAI version][Deployed @412 Food Rescue]

Draining the Water Hole: Mitigating Social Engineering Attacks with CyberTWEAK
Zheyuan Ryan Shi, Aaron Schlenker, Brian Hay, Daniel Bittleston, Siyu Gao, Emily Peterson, John Trezza, Fei Fang
IAAI-20: 32nd Annual Conference on Innovative Applications of Artificial Intelligence
[Abstract][IAAI version][full version][Software @Chrome Web Store]

Approximated Temporal-Induced Neural Self-Play for Finitely Repeated Bayesian Games
Zihan Zhou, Zheyuan Ryan Shi, Yi Wu, Fei Fang
Working paper, 2020. Appeared at AAAI-20 workshop.

Learning and Planning in the Feature Deception Problem
Zheyuan Ryan Shi, Ariel D. Procaccia, Kevin S. Chan, Sridhar Venkatesan, Noam Ben-Asher, Nandi O. Leslie, Charles Kamhoua, Fei Fang
Working paper, 2019. Appeared at EC-19, IJCAI-19 workshops.
[Abstract][full version]

Deep Reinforcement Learning for Green Security Games with Real-Time Information
Yufei Wang, Zheyuan Ryan Shi, Lantao Yu, Yi Wu, Rohit Singh, Lucas Joppa, Fei Fang
AAAI-19: the Thirty-Third AAAI Conference on Artificial Intelligence
[Abstract][AAAI version][full version] [source code] [slides]

Designing the Game to Play: Optimizing Payoff Structure in Security Games
Zheyuan Ryan Shi, Ziye Tang, Long Tran-Thanh, Rohit Singh, Fei Fang
IJCAI-ECAI-18: the 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence.
[Abstract] [IJCAI version] [full version] [source code] [slides]

Optimizing Peer Teaching to Enhance Team Performance
Zheyuan Ryan Shi, Fei Fang
TEAMAS-17: First International Workshop on Teams in Multiagent Systems, at AAMAS-17
In Autonomous Agents and Multiagent Systems: AAMAS 2017 Workshops, Best Papers, Springer.
Winner of Best Paper
[Abstract] [Springer version]

Strategic Reporting in Exponential Family Prediction Markets
Zheyuan Ryan Shi, Sindhu Kutty
URTC-16: 2016 MIT IEEE Undergraduate Research Technology Conference
[Abstract] [IEEE version]