Awesome Reinforcement Learning
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Lihong Li — most-cited papers & profile · Reinforcement Learning
← authors
·
overview
Lihong Li
5
papers ·
277
citations ·
33
h-index
Hebei University of Engineering · North China University of Science and Technology · TED University · Hangzhou Dianzi University · Shanxi Datong University · Shenyang Jianzhu University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
2018 · 112 citations
AlgaeDICE: Policy Gradient from Arbitrary Experience
2019 · 82 citations
Stochastic Variance Reduction Methods for Policy Evaluation
2017 · 69 citations
CoinDICE: Off-Policy Confidence Interval Estimation
2020 · 12 citations
On the Optimality of Batch Policy Optimization Algorithms
2021 · 2 citations
Top co-authors
Dale Schuurmans
· 3
Csaba Szepesvari
· 2
Dengyong Zhou
· 2
Ofir Nachum
· 2
Yinlam Chow
· 2
Bo Dai
· 1
Bo Dai
· 1
Bo Dai
· 1
Chenjun Xiao
· 1
Ilya Kostrikov
· 1
Jianshu Chen
· 1
Jincheng Mei
· 1
Topics
Offline RL
Value-Based
Policy Gradient
Exploration