Lihong Li
Artificial Intelligence · 2006–2020
A researcher in the Science corpus: 68 papers; trusts 1,937 researchers and is trusted by 4,251 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,562 citations into it; #307 of 36,961 by trust here, #368 by citations
- Reinforcement Learning — 952 citations into it; #40 of 2,250 by trust here, #55 by citations
- Management Science and Operations Research — 485 citations into it; #21 of 12,201 by trust here, #23 by citations
- Natural Language Processing — 310 citations into it; #1,274 of 5,725 by trust here, #847 by citations
- Statistics and Probability — 259 citations into it; #241 of 13,188 by trust here, #327 by citations
- Control and Systems Engineering — 257 citations into it; #125 of 8,519 by trust here, #118 by citations
- Computer Vision and Pattern Recognition — 207 citations into it; #9,797 of 21,973 by trust here, #6,987 by citations
- Optimization & Training — 151 citations into it; #405 of 2,605 by trust here, #366 by citations
Whom Lihong Li trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard S. Sutton
- Sham M. Kakade
- J. Langford
- Alexander L. Strehl
- Andrew Barto
- Michael Kearns
- Martin L. Puterman
- Peter Auer
- Michael L. Littman
- Geoffrey E. Hinton
Who trusts Lihong Li overall
- Nathan Kallus
- Nan Jiang
- Ofir Nachum
- Sergey Levine
- Emma Brunskill
- Ziyang Tang
- Michael L. Littman
- Alekh Agarwal
- Susan Athey
- Bo Dai
Papers from Lihong Li's perspective
Ordered by how strongly the researchers Lihong Li trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Parallelized Stochastic Gradient Descent (2010) — 1,440 citations
- A contextual-bandit approach to personalized news article recommendation (2010) — 3,422 citations
- An Empirical Evaluation of Thompson Sampling (2011) — 1,641 citations
- Doubly Robust Off-policy Value Evaluation for Reinforcement Learning (2015) — 735 citations
- Towards a Unified Theory of State Abstraction for MDPs (2006) — 577 citations
- Neural Approaches to Conversational AI (2018) — 750 citations
- PAC model-free reinforcement learning (2006) — 527 citations
- Sparse Online Learning via Truncated Gradient (2008) — 502 citations
- Deep Reinforcement Learning with a Natural Language Action Space (2015) — 268 citations
- Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms (2010) — 614 citations
- A Bayesian Sampling Approach to Exploration in Reinforcement Learning (2009) — 192 citations
- An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning (2008) — 224 citations
- Reinforcement Learning in Finite MDPs: PAC Analysis (2009) — 339 citations
- Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits (2014) — 564 citations
- Recurrent Reinforcement Learning: A Hybrid Approach (2015) — 77 citations
- Learning from Logged Implicit Exploration Data (2010) — 267 citations
- Knows what it knows: a framework for self-aware learning (2008) — 259 citations
- BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems (2016) — 173 citations
- DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections (2019) — 373 citations
- Efficient Exploration for Dialog Policy Learning with Deep BBQ Networks \& Replay Buffer Spiking (2016) — 58 citations