Peter Marbach

Reinforcement Learning · 1998–2003

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

Subfields

• Reinforcement Learning — 9 citations into it; #1,955 of 2,242 by trust here, #2,125 by citations

Whom Peter Marbach trusts overall

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

1. Peter W. Glynn
2. Ronald J. Williams
3. Tommi S. Jaakkola
4. Dimitri P. Bertsekas
5. John N. Tsitsiklis
6. Richard S. Sutton
7. Satinder Singh
8. Pierre L'Ecuyer
9. Michael I. Jordan
10. Andrew Barto

Who trusts Peter Marbach overall

1. Huizhen Yu
2. Pawel Wawrzynski
3. Aviv Tamar
4. Richard S. Sutton
5. Vijay R. Konda
6. John N. Tsitsiklis
7. Jonathan Baxter
8. Dimitri P. Bertsekas
9. Lex Weaver
10. Sham M. Kakade

Papers from Peter Marbach's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
3. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
4. Gradient-based learning applied to document recognition
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. Nonlinear Programming
7. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
8. ImageNet: A large-scale hierarchical image database
9. Long Short-Term Memory
10. Attention is All you Need (Neural Information Processing Systems)

Their papers

• Approximate Gradient Methods in Policy-Space Optimization of Markov Reward Processes (2003) — 71 citations
• Simulation-based optimization of Markov reward processes (1998)