Yu Bai

Beyond Linearization: On Quadratic and Higher-Order Approximation of\n Wide Neural Networks

Yu Bai, Jason D. Lee · arXiv (Cornell University) · 2019 · 44 citations · Full text

Provable Self-Play Algorithms for Competitive Reinforcement Learning

Yu Bai, Chi Jin · arXiv (Cornell University) · 2020 · 30 citations · Full text

Artificial Intelligence, Engineering, Game Theory +17

Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning

Yu Bai, Yu-Xiang Wang · arXiv (Cornell University) · 2020 · 24 citations · Full text

Provably Efficient Q-Learning with Low Switching Cost

Yu Bai, Tengyang Xie, Nan Jiang et al. · arXiv (Cornell University) · 2019 · 22 citations · Full text

Artificial Intelligence, Mathematical Programming, Engineering +14

A Sharp Analysis of Model-based Reinforcement Learning with Self-Play

Qinghua Liu, Tiancheng Yu, Yu Bai et al. · International Conference on Machine Learning · 2021 · 21 citations

Artificial Intelligence, Multi-agent Reinforcement Learning, Engineering +23