Tiancheng Yu's Homepage

Tiancheng Yu (余天呈)

yutc [at] mit [dot] edu

I am a 5th-year PhD student in MIT EECS, advised by Prof. Suvrit Sra. I got my Master degree in EECS at MIT in 2020. Before MIT, I was an undergraduate student in Tsinghua University, major in Electronic Engineering and minor in Statistics. I was fortunate to be advised by Prof. Yuan Shen.

In Fall 2019, I visited Princeton Univerisity and worked with Prof. Chi Jin. In Summer 2017, I was fortunate to join Stanford UGVR program and advised by Prof. Tsachy Weissman. In Fall 2016, I was an exchange student in University of Wisconsin, Madison and worked with Prof. Dimitris Papailiopoulos.

I'm interested in the theory of Reinforcement Learning (RL), especially sample efficiency, robustness and function approximation.

Selected Publications

*: equal contribution or alphabetical order.

Mingyang Liu*, Asuman Ozdaglar*, Tiancheng Yu* and Kaiqing Zhang*. The Power of Regularization in Solving Extensive-Form Games. ICLR 2023.
Yu Bai*, Chi Jin*, Song Mei*, Ziang Song* and Tiancheng Yu*. Efficient Φ-Regret Minimization in Extensive-Form Games via Online Mirror Descent. NeurIPS 2022 Oral.
Yu Bai*, Chi Jin*, Song Mei* and Tiancheng Yu*. Near-Optimal Learning of Extensive-Form Games with Imperfect Information. ICML 2022. Preliminary version presented as contributed talk at the ICLR 2022 Workshop on Gamification and Multiagent Solutions.
Chi Jin*, Qinghua Liu*, Yuanhao Wang* and Tiancheng Yu*. V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL. Submitted. Preliminary version selected as Best Paper at the ICLR 2022 Workshop on Gamification and Multiagent Solutions.
Chi Jin*, Qinghua Liu* and Tiancheng Yu*. The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces. ICML 2022. Preliminary version presented on ICML 2021 Workshop on Reinforcement Learning Theory.
Tiancheng Yu, Yi Tian, Jingzhao Zhang and Suvrit Sra. Provably Efficient Algorithms for Multi-Objective Competitive RL. ICML 2021 Long Presentation (Top 3%).
Yi Tian*, Yuanhao Wang*, Tiancheng Yu* and Suvrit Sra. Online Learning in Unknown Markov Games. ICML 2021.
Qinghua Liu, Tiancheng Yu, Yu Bai and Chi Jin. A Sharp Analysis of Model-based Reinforcement Learning with Self-Play. ICML 2021.
Chi-Ning Chou*, Juspreet Singh Sandhu*, Mien Brabeeba Wang* and Tiancheng Yu*. A General Framework for Analyzing Stochastic Dynamics in Learning Algorithms. Submitted.
Yu Bai*, Chi Jin* and Tiancheng Yu*. Near-Optimal Reinforcement Learning with Self-Play. NeurIPS 2020. Preliminary version presented on ICML 2020 Theoretical Foundations of RL workshop. Short talk (Top 6%).
Chi Jin*, Akshay Krishnamurthy*, Max Simchowitz* and Tiancheng Yu*. Reward-Free Exploration for Reinforcement Learning. ICML 2020.
Chi Jin*, Tiancheng Jin*, Haipeng Luo*, Suvrit Sra* and Tiancheng Yu*. Learning Adversarial MDPs with Bandit Feedback and Unknown Transition. ICML 2020.
Yanjun Han*, Jiantao Jiao*, Chuan-Zheng Lee*, Tsachy Weissman*, Yihong Wu* and Tiancheng Yu*. Entropy Rate Estimation for Markov Chains with Large State Space. NIPS 2018.

Teaching

MIT 6.246 Reinforcement Learning: Foundations And Methods . Teaching Assistant. Spring 2021.
MIT 6.7900 Machine Learning . Teaching Assistant. Fall 2022.

Miscellaneous

I enjoy piano and vocal (Bel-Canto) performing in my spare time. I am fortunate to learn from the inspiring musicians Xiaopei Xu, Jen-tao Yu, Bingchuan Wan, Yongqian zhang (张永前) and Linbo Fu (付林波).
I used to do competitive bodybuilding and join the Varsity Team in Tsinghua in 2016. Later I gradually switch to powerlifting. I am fortunate to learn from the fantastic athletes and coaches Dan Green, Cheng Tang (唐诚) and Chenyu Mao (毛晨雨).
I became a big fan of Poker after taking the fantastic course 15.S50 Poker Theory and Analytics . Poker provides me with a lot of inspiration in studying sequential decision making problems! Personal best: 3-rd place (3/~150) in Harvard-MIT poker tournament main event, Spring 2020.
I have always been a hungary reader in literature, history and (social) science since childhood. I began to write about my PhD life in WeChat Blog "余在水 " since May 2020. The articals are based on my personal communication with my family. Check it out!
I translated the cute AI book "You Look Like a Thing and I Love You: How Artificial Intelligence Works and Why It's Making the World a Weirder Place " into Chinese:《你看起来好像……我爱你(AI的工作原理以及它为这个世界带来的稀奇古怪)》(Janelle Shane著, 中信出版集团）. Check it out!