David S. Leslie
Artificial Intelligence · 2006–2012
A researcher in the Science corpus: 2 papers; trusts 16 researchers and is trusted by 6 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 13 citations into it
- Management Science and Operations Research — 13 citations into it; #6,563 of 11,946 by trust here, #6,314 by citations
- Reinforcement Learning — 11 citations into it; #1,852 of 2,242 by trust here, #1,778 by citations
- Economics and Econometrics — 5 citations into it
Whom David S. Leslie trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard S. Sutton
- Josef Hofbauer
- Drew Fudenberg
- Sergiu Hart
- Tilman Börgers
- Peter Auer
- Andrew Barto
- Satinder Singh
- T. L. Lai Andherbertrobbins
- Alvin E. Roth
Who trusts David S. Leslie overall
- Johannes Heinrich
- Francisco S. Melo
- David Silver
- Manuel Lopes
- Jason R. Marden
- Manuela M. Veloso
- Shipra Agrawal
- Gürdal Arslan
- Marc Lanctot
Papers from David S. Leslie's perspective
Ordered by how strongly the researchers David S. Leslie trusts endorse each paper. Same corpus, a different order for every researcher.
- Reinforcement Learning: An Introduction
- ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLES
- Asymptotically Efficient Adaptive Allocation Rules
- The Theory of Learning in Games
- Finite-time Analysis of the Multiarmed Bandit Problem
- Using Confidence Bounds for Exploitation-Exploration Trade-offs
- A contextual-bandit approach to personalized news article recommendation
- Convergence Results for Single-Step On-Policy Reinforcement-Learning Algorithms
- Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
- Introduction to Reinforcement Learning
Their papers
- Generalised weakened fictitious play (2006) — 174 citations
- Optimistic Bayesian Sampling in Contextual-Bandit Problems (2012) — 139 citations