Christopher J. C. H. Watkins

Reinforcement Learning · with Dayan · 1992–2006

A researcher in the Science corpus: 3 papers; trusts 2 researchers and is trusted by 577 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 6 citations into it; #51 of 2,242 by trust here, #114 by citations

Whom Christopher J. C. H. Watkins trusts overall

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

1. Richard S. Sutton
2. Longxin Lin
3. David Chapman
4. Leslie Pack Kaelbling
5. Harold J. Kushner
6. Andrew Barto

Who trusts Christopher J. C. H. Watkins overall

1. J. Urgen Schmidhuber
2. Sergey Levine
3. Hado van Hasselt
4. Marc G. Bellemare
5. Pawel Wawrzynski
6. Yoshua Bengio
7. Zachary Chase Lipton
8. C. Drummond
9. Jianfeng Gao
10. Stefano V. Albrecht

Papers from Christopher J. C. H. Watkins's perspective

Ordered by how strongly the researchers Christopher J. C. H. Watkins trusts endorse each paper. Same corpus, a different order for every researcher.

1. Input Generalization in Delayed Reinforcement Learning: An Algorithm and Performance Comparisons
2. Self-improving reactive agents based on reinforcement learning, planning and teaching
3. Learning from delayed rewards
4. wchastic. approximation methods for constrained and unconstrained systems
5. Temporal credit assignment in reinforcement learning
6. Dynamic Programming and Markov Processes
7. Learning internal representations by error propagation
8. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
9. Residual Algorithms: Reinforcement Learning with Function Approximation
10. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Their papers

• Technical Note: Q-Learning (2004) — 2,385 citations
• Reinforcement Learning: A Computational Perspective (2006) — 18 citations
• Q-learning (1992)