Gen Li

发表

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

Gen Li, 2022 .

Model-Based Reinforcement Learning Is Minimax-Optimal for Offline Zero-Sum Markov Games

Jianqing Fan, Yuxin Chen, Yuling Yan, 2022, ArXiv.

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity

Yuxin Chen, Yuejie Chi, Yuting Wei, 2022, ICML.

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity

Yuxin Chen, Yuejie Chi, Yuting Wei, 2022, ICML.

Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model

Yuxin Chen, Yuejie Chi, Yuting Wei, 2022, ArXiv.

Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model

Yuxin Chen, Yuejie Chi, Yuting Wei, 2022, NeurIPS.

Settling the Sample Complexity of Model-Based Offline Reinforcement Learning

Yuxin Chen, Yuejie Chi, Yuting Wei, 2022, ArXiv.

Pessimism for Offline Linear Contextual Bandits using 𝓁p Confidence Sets

Nathan Srebro, Cong Ma, Gen Li, 2022, NeurIPS.

Exponential Family Model-Based Reinforcement Learning via Score Matching

Nathan Srebro, Zhuoran Yang, Zhaoran Wang, 2021, NeurIPS.

A Non-Asymptotic Framework for Approximate Message Passing in Spiked Models

Yuting Wei, Gen Li, 2022, ArXiv.

Specializing Versatile Skill Libraries using Local Mixture of Experts

Gerhard Neumann, Onur Celik, Philipp Becker, 2021, CoRL.

Approximate message passing from random initialization with applications to ℤ2 synchronization

Wei Fan, Yuting Wei, Gen Li, 2023, Proceedings of the National Academy of Sciences of the United States of America.

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis

Ee, Yuting Wei, Gen Li, 2021, Operations Research.

Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models

Yuxin Chen, Yuejie Chi, Yuting Wei, 2023, ArXiv.

The Efficacy of Pessimism in Asynchronous Q-Learning

Jianqing Fan, Yuxin Chen, Yuling Yan, 2022, IEEE Transactions on Information Theory.

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

Yuxin Chen, Yuejie Chi, M. Geist, 2023, ArXiv.

Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning

Yuxin Chen, Yuling Yan, Gen Li, 2023, ArXiv.

Sharp high-probability sample complexities for policy evaluation with linear function approximation

A. Rinaldo, Yuejie Chi, Yuting Wei, 2023, arXiv.org.

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

Jason D. Lee, Yuxin Chen, Yuejie Chi, 2023, ArXiv.

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

Gen Li, 2022 .

Learning Topological Motion Primitives for Knot Planning

Gen Li, Yilin Zhu, J. Bohg, 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Approximate message passing from random initialization with applications to ℤ2 synchronization

Yuting Wei, Gen Li, Wei Fan, 2023, Proceedings of the National Academy of Sciences of the United States of America.

Understanding the Eluder Dimension

Dylan J. Foster, Pritish Kamath, Gen Li, 2021, NeurIPS.

Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time

Gen Li, Xiang Ji, 2023, ArXiv.

Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods

Yuxin Chen, Yuejie Chi, H. Poor, 2023, ArXiv.

Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models

Yuxin Chen, Yuejie Chi, Yuting Wei, 2023, ArXiv.

Settling the Sample Complexity of Model-Based Offline Reinforcement Learning

Yuxin Chen, Yuejie Chi, Yuting Wei, 2022, ArXiv.