Yingru Li
Yingru Li
Home
Talks
Publications
Contact
Resume
RL-Seminar
Light
Dark
Automatic
Regret
HyperAgent - A Simple, Efficient, Scalable and Provable RL Framework
Practically and provably efficient RL under resource constraints!
Mar 23, 2024 1:30 PM
Rice University
Yingru LI
Slides
Video
Follow
HyperAgent - A Simple, Efficient and Scalable RL Framework for Complex Environments
Practically and provably efficient RL under resource constraints!
Jan 13, 2024 1:20 PM
Daoyuan Building
Yingru LI
Slides
Follow
News
Optimistic Thompson Sampling for No-Regret Learning in Unknown Games
Many real-world problems involving multiple decision-makers can be modeled as an unknown game characterized by bandit feedback. …
Yingru Li
,
Liangqi Liu
,
Wenqiang Pu
,
Zhi-Quan Luo
Cite
arXiv
Prior-dependent analysis of posterior sampling reinforcement learning with function approximation
This paper delves into the Bayesian regret of posterior sampling reinforcement learning (PSRL) and presents a novel prior-dependent regret bound within the linear mixture model. The bound hinges on the variance of the underlying MDP in the prior distribution, offering a distinctive perspective in the realm of randomized exploration.
Yingru Li
,
Zhi-Quan Luo
Cite
Provably scalable and near-optimal Thompson sampling via hypermodel with applications in decision-making language agents
Hypermodel for efficient incremental approximation of the posterior (uncertainty quantification) over complex models without leveraging conjugacy as encountering more data; Index sampling for approximate posterior sampling for data-efficient sequential decision-making. This approach is provably superior than ensemble sampling and Langevin Monte-carlo.
Yingru Li
,
Jiawei Xu
,
Zhi-Quan Luo
Cite
Towards AGI for Humanity through Efficient Reinforcement Learning
Addressing efficiency chanllenge in RL by HyperFQI algorithm
Oct 21, 2023 2:30 PM
Teaching B Building
Yingru LI
Slides
Follow
Efficient and scalable reinforcement learning via hypermodel
Addressing efficiency challenge in RL with theoretical advancements and practical algorithm designs.
Yingru Li
,
Jiawei Xu
,
Zhiquan Luo
PDF
Cite
Poster
Slides
Website
No-Regret Learning in Unknown Game with Applications
Aug 23, 2022 2:00 PM
Yingru LI
Slides
Follow
Cite
×