World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
42
Citations
16244
World Ranking
8151
National Ranking
3492

Overview

Lihong Li is a researcher affiliated with Amazon in the United States. Their academic contributions span multiple fields, primarily focused on Computer Science and Engineering. Within these domains, they have emphasized specific subfields such as Computer Vision and Pattern Recognition, Artificial Intelligence, Management Science and Operations Research, Biomedical Engineering, and Industrial and Manufacturing Engineering.

The scientist's publications cover a range of topics. Their main research interests include Reinforcement Learning in Robotics, Advanced Bandit Algorithms Research, Machine Learning and Algorithms, Photoacoustic and Ultrasonic Imaging, Video Surveillance and Tracking Methods, Advanced Neural Network Applications, and Advanced Image and Video Retrieval Techniques.

Frequent publication venues for their work include:

  • arXiv (Cornell University)
  • Journal of Advanced Computational Intelligence and Intelligent Informatics
  • Sensors
  • The Visual Computer
  • BioMedical Engineering OnLine

Among recent papers, the following are notable examples across different years and venues:

  • Multipath affinage stacked-hourglass networks for human pose estimation, 2020, Frontiers of Computer Science
  • Understanding Domain Randomization for Sim-to-real Transfer, 2021, arXiv (Cornell University)
  • Exploration of the correlation between GPCRs and drugs based on a learning to rank algorithm, 2020, Computers in Biology and Medicine
  • A Conceptual Framework for Collaborative Development of Intelligent Construction and Building Industrialization, 2022, Frontiers in Environmental Science
  • Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning, 2020, arXiv (Cornell University)

Lihong Li has collaborated with several frequent coauthors, including:

  • Pengtao Wang
  • Jiachen Hu
  • Liwei Wang
  • Feiyang Pan
  • Ziwei Zeng

Best Publications

  • A contextual-bandit approach to personalized news article recommendation

    Lihong Li;Wei Chu;John Langford;Robert E. Schapire

  • Parallelized Stochastic Gradient Descent

    Martin Zinkevich;Markus Weimer;Lihong Li;Alex J. Smola

  • An Empirical Evaluation of Thompson Sampling

    Olivier Chapelle;Lihong Li

  • Contextual bandits with linear Payoff functions

    Wei Chu;Lihong Li;Lev Reyzin;Robert E. Schapire

  • Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms

    Lihong Li;Wei Chu;John Langford;Xuanhui Wang

  • Sparse Online Learning via Truncated Gradient

    John Langford;Lihong Li;Tong Zhang

  • PAC model-free reinforcement learning

    Alexander L. Strehl;Lihong Li;Eric Wiewiora;John Langford

  • Doubly Robust Policy Evaluation and Learning

    John Langford;Lihong Li;Miroslav Dud k

  • Doubly Robust Policy Evaluation and Learning

    Miroslav Dudik;John Langford;Lihong Li

  • Doubly robust off-policy value evaluation for reinforcement learning

    Nan Jiang;Lihong Li

  • Towards a Unified Theory of State Abstraction for MDPs.

    Lihong Li;Thomas J. Walsh;Michael L. Littman

  • Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits

    Alekh Agarwal;Daniel Hsu;Satyen Kale;John Langford

  • Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

    Bhuwan Dhingra;Lihong Li;Xiujun Li;Jianfeng Gao

  • Reinforcement Learning in Finite MDPs: PAC Analysis

    Alexander L. Strehl;Lihong Li;Michael L. Littman

  • Knows what it knows: a framework for self-aware learning

    Lihong Li;Michael L. Littman;Thomas J. Walsh

  • Knows what it knows: a framework for self-aware learning

    Lihong Li;Michael L. Littman;Thomas J. Walsh;Alexander L. Strehl

  • Doubly robust policy evaluation and optimization

    Miroslav Dudík;Dumitru Erhan;John Langford;Lihong Li

  • Contextual Bandit Algorithms with Supervised Learning Guarantees

    Alina Beygelzimer;John Langford;Lihong Li;Lev Reyzin

  • An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning

    Ronald Parr;Lihong Li;Gavin Taylor;Christopher Painter-Wakefield

  • BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems

    Unknown

  • Learning from Logged Implicit Exploration Data

    Alex Strehl;John Langford;Lihong Li;Sham M Kakade

  • Neural Approaches to Conversational AI.

    Jianfeng Gao;Michel Galley;Lihong Li

Frequent Co-Authors

Jianfeng Gao
Jianfeng Gao Microsoft (United States)
John Langford
John Langford Microsoft (United States)
Michael L. Littman
Michael L. Littman Brown University
Li Deng
Li Deng Citadel
Dengyong Zhou
Dengyong Zhou Google (United States)
Dale Schuurmans
Dale Schuurmans University of Alberta
Emma Brunskill
Emma Brunskill Stanford University
Russell Greiner
Russell Greiner University of Alberta
Asli Celikyilmaz
Asli Celikyilmaz Facebook (United States)
Zachary C. Lipton
Zachary C. Lipton Carnegie Mellon University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring computer science in the USA opens up a range of flexible and affordable online study options. Many students seek the most affordable online colleges to keep costs manageable. These institutions often provide quality programs recognized by employers, without the high price tag.

Worried about past academic performance? You can still qualify for leading computer science programs. Check out the best colleges for low gpa, which support students who may not meet the standard entry criteria but are eager to build tech skills and launch their careers.

If you're motivated to earn your degree quicker, consider an accelerated computer science degree online. Accelerated programs can fast-track your graduation and entry into the tech workforce.

A computer science foundation also paves the way for interdisciplinary careers. For example, learn what can i do with an environmental science degree to see how programming and data analysis skills intersect with fields like environmental science, expanding your job prospects even further.

Best Scientists Citing Lihong Li

Trending Scientists

Recently Published Articles