Daniil Ryabko

Artificial Intelligence · 2015

A researcher in the Science corpus: 1 paper; trusts 13 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 7 citations into it
• Management Science and Operations Research — 5 citations into it
• Reinforcement Learning — 5 citations into it

Whom Daniil Ryabko trusts overall

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

1. Robert D. Kleinberg
2. Michael Kearns
3. Peter L. Bartlett
4. Yasin Abbasi-Yadkori

Papers from Daniil Ryabko's perspective

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

1. Near-Optimal Reinforcement Learning in Polynomial Time
2. Near-optimal Regret Bounds for Reinforcement Learning
3. The Nonstochastic Multiarmed Bandit Problem
4. Online Linear Regression and Its Application to Model-Based Reinforcement Learning
5. Introduction to Nonparametric Estimation
6. Nearly Tight Bounds for the Continuum-Armed Bandit Problem
7. Exploration in Metric State Spaces
8. Off-policy Learning with Options and Recognizers
9. Multi-armed bandits in metric spaces (Symposium on the Theory of Computing)
10. Kernel-Based Reinforcement Learning

Their papers

• Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning (2015) — 41 citations