Mark Lee

Reinforcement Learning · 2007–2009

A researcher in the Science corpus: 2 papers; trusts 30 researchers and is trusted by 38 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 43 citations into it; #466 of 2,242 by trust here, #819 by citations
• Artificial Intelligence — 14 citations into it; #7,461 of 35,345 by trust here, #10,942 by citations
• Optimization & Training — 5 citations into it

Whom Mark Lee trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Richard S. Sutton
2. Andrew Barto
3. John N. Tsitsiklis
4. Jan Peters
5. Sham M. Kakade
6. Dimitri P. Bertsekas
7. Ronald J. Williams
8. Vivek Shripad Borkar
9. Satinder Singh
10. Vijay R. Konda

Who trusts Mark Lee overall

1. Philip S. Thomas
2. Kamil Andrzej Ciosek
3. Shalabh Bhatnagar
4. Ivo Grondman
5. Pawel Wawrzynski
6. Mohammad Ghavamzadeh
7. Thomas Degris
8. Shimon Whiteson
9. Csaba Szepesvari
10. Hamid Reza Maei

Papers from Mark Lee's perspective

Ordered by how strongly the researchers Mark Lee trusts endorse each paper. Same corpus, a different order for every researcher.

1. Reinforcement Learning: An Introduction
2. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
3. Policy Gradient Methods for Reinforcement Learning with Function Approximation
4. ImageNet classification with deep convolutional neural networks
5. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
6. Markov Decision Processes: Discrete Stochastic Dynamic Programming
7. Linear Least-Squares algorithms for temporal difference learning
8. Gradient-based learning applied to document recognition
9. Residual Algorithms: Reinforcement Learning with Function Approximation
10. Natural Gradient Works Efficiently in Learning

Their papers

• Natural actor-critic algorithms (2009) — 649 citations
• Incremental Natural Actor-Critic Algorithms (2007) — 213 citations