Author

Runlong Zhou

Tsinghua University

h-index 8 View on Semantic Scholar

We have 1 of 17 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence

A new bound on total deviation for time-homogeneous MDPs is proved and a cutting bonus that preserves both optimism and the monotonicity needed for planning is designed that preserves both optimism and the monotonicity needed for planning.

Runlong Zhou, Zi-Han Zhang, Maryam Fazel et al. · arXiv.org · 0 citations