Liyu Chen

I am a research scientist at ByteDance, working on alignment for large language models (LLM). I obtained my PhD from University of Southern California, where I was very fortunate to be advised by Prof. Haipeng Luo. My research interest lies in online learning and reinforcement learning.

I did my bachelors at the Hong Kong Universiy of Science and Technology and did my final year thesis with Prof. Dit-Yan Yeung.

Email  /  CV

profile photo
Experiences

  • [Summer 2022] Research intern at Facebook France supervised by Matteo Pirotta and Alessandro Lazaric, working on goal-oriented reinforcement learning and reward-free autonomous exploration of unknown environment.

  • [Summer 2019] Research intern at ByteDance Inc supervised by Chong Wang, working on item cold start recommendation.

  • [Summer 2015] Summer intern at LSCM R&D Centre, working on baggage recognition in airports.

Publications
B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
Zishun Yu, Yunzhe Tao, Liyu Chen, Tao Sun, Hongxia Yang
ICLR, 2024
Online Learning for Stochastic Shortest Path Model via Posterior Sampling
Mehdi Jafarnia-Jahromi, Liyu Chen, Rahul Jain, Haipeng Luo
UAI, 2023
Layered State Discovery for Incremental Autonomous Exploration
Liyu Chen, Andrea Tirinzoni, Alessandro Lazaric, Matteo Pirotta
ICML, 2023
Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path
Liyu Chen, Andrea Tirinzoni, Matteo Pirotta, Alessandro Lazaric
ALT, 2023
Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments
Liyu Chen, Haipeng Luo
NeurIPS, 2022
Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback
Yan Dai, Haipeng Luo, Liyu Chen
NeurIPS, 2022
Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP
Liyu Chen, Rahul Jain, Haipeng Luo
ICML, 2022 (Long Talk) [slides]
Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints
Liyu Chen, Rahul Jain, Haipeng Luo
ICML, 2022 [slides]
Policy Optimization for Stochastic Shortest Path
Liyu Chen, Haipeng Luo, Aviv Rosenberg
COLT, 2022 [slides]
Policy Learning and Evaluation with Randomized Quasi-Monte Carlo
Sébastien Arnold, Pierre L'Ecuyer, Liyu Chen, Yi-fan Chen, Fei Sha
AISTATS, 2022
Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path
Liyu Chen, Mehdi Jafarnia-Jahromi, Rahul Jain, Haipeng Luo
NeurIPS, 2021 [slides]
Finding the Stochastic Shortest Path with Low Regret: The Adversarial Cost and Unknown Transition Case
Liyu Chen, Haipeng Luo
ICML, 2021 [slides]
Impossible Tuning Made Possible: A New Expert Algorithm and Its Applications
Liyu Chen*, Chen-Yu Wei*, Haipeng Luo*
COLT, 2021 [slides]
Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition
Liyu Chen, Chen-Yu Wei, Haipeng Luo
COLT, 2021 [slides]
Hyper-parameter Tuning under a Budget Constraint
Zhiyun Lu, Liyu Chen, Chao-Kai Chiang, Fei Sha
IJCAI, 2019
Synthesized Policies for Transfer and Adaptation across Tasks and Environments
Hexiang Hu*, Liyu Chen*, Boqing Gong, Fei Sha
NeurIPS, 2018 (Spotlight)

Website designed by Jon Barron