Mark D. Pendrith

Reinforcement Learning · 1994–1999

A researcher in the Science corpus: 3 papers; trusts 2 researchers and is trusted by 6 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 6 citations into it; #1,075 of 2,242 by trust here, #1,999 by citations

Whom Mark D. Pendrith trusts overall

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

1. Richard S. Sutton
2. Harold J. Kushner
3. Robert A. Jacobs
4. Maja J. Mataric
5. Andrew Barto
6. Ben J. A. Kröse
7. Satinder Singh
8. Ronald J. Williams
9. Martin L. Puterman

Who trusts Mark D. Pendrith overall

1. Kenneth O. Stanley
2. Risto Miikkulainen
3. Roy Fox
4. Pawea Cichosz
5. Jens Kober
6. Ari Pakman
7. Faustino J. Gomez
8. Naftali Tishby

Papers from Mark D. Pendrith's perspective

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

1. Reward Functions for Accelerated Learning
2. wchastic. approximation methods for constrained and unconstrained systems
3. Increased rates of convergence through learning rate adaptation
4. Learning from delayed rewards
5. Gradient-based learning applied to document recognition
6. Learning internal representations by error propagation
7. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
8. ImageNet classification with deep convolutional neural networks
9. Reinforcement Learning: An Introduction
10. On the Convergence of Stochastic Iterative Dynamic Programming Algorithms

Their papers

• Reinforcement Learning in Situated Agents: Theoretical and Practical Solutions (1999)
• Estimator Variance in Reinforcement Learning: Theoretical Problems and Practical Solutions (1997)
• On Reinforcement Learning of Control Actions in Noisy and Non-Markovian Domains (1994)