Thomas Jaksch

Reinforcement Learning · 2008

A researcher in the Science corpus: 1 paper; trusts 7 researchers and is trusted by 98 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 11 citations into it; #238 of 2,242 by trust here, #494 by citations
• Artificial Intelligence — 10 citations into it; #2,231 of 35,345 by trust here, #5,187 by citations
• Management Science and Operations Research — 8 citations into it; #318 of 11,946 by trust here, #497 by citations
• Statistics and Probability — 5 citations into it

Whom Thomas Jaksch trusts overall

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

1. Alexander L. Strehl
2. Peter Auer
3. Michael L. Littman
4. Richard S. Sutton
5. Martin L. Puterman
6. Nicolò Cesa-Bianchi
7. David Freedman
8. Andrew Barto
9. Ambuj Tewari
10. Peter L. Bartlett

Who trusts Thomas Jaksch overall

1. Ian Osband
2. Kamyar Azizzadenesheli
3. Benjamin Van Roy
4. Emma Brunskill
5. Christoph Dann
6. Chi Jin
7. Sergey Levine
8. Tor Lattimore
9. Ronald Ortner
10. Zihan Zhang

Papers from Thomas Jaksch's perspective

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

1. Reinforcement Learning: An Introduction
2. Markov Decision Processes: Discrete Stochastic Dynamic Programming
3. An analysis of model-based Interval Estimation for Markov Decision Processes
4. PAC model-free reinforcement learning
5. The Nonstochastic Multiarmed Bandit Problem
6. On Tail Probabilities for Martingales
7. Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs
8. Optimal Adaptive Policies for Markov Decision Processes
9. WEIGHTED SUMS OF CERTAIN DEPENDENT RANDOM VARIABLES
10. ImageNet classification with deep convolutional neural networks

Their papers

• Near-optimal Regret Bounds for Reinforcement Learning (2008) — 1,579 citations