Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Tor Lattimore

Tor Lattimore

An Information-Theoretic Approach to Minimax Regret in Partial Monitoring

Feb 01, 2019
Tor Lattimore, Csaba Szepesvari

Figure 1 for An Information-Theoretic Approach to Minimax Regret in Partial Monitoring

Figure 2 for An Information-Theoretic Approach to Minimax Regret in Partial Monitoring

Figure 3 for An Information-Theoretic Approach to Minimax Regret in Partial Monitoring

Figure 4 for An Information-Theoretic Approach to Minimax Regret in Partial Monitoring

* 26 pages

Access Paper or Ask Questions

Soft-Bayes: Prod for Mixtures of Experts with Log-Loss

Jan 08, 2019
Laurent Orseau, Tor Lattimore, Shane Legg

* Algorithmic Learning Theory 2017

Access Paper or Ask Questions

Single-Agent Policy Tree Search With Guarantees

Nov 28, 2018
Laurent Orseau, Levi H. S. Lelis, Tor Lattimore, Théophane Weber

Figure 1 for Single-Agent Policy Tree Search With Guarantees

Figure 2 for Single-Agent Policy Tree Search With Guarantees

Figure 3 for Single-Agent Policy Tree Search With Guarantees

* 32nd Conference on Neural Information Processing Systems (NIPS 2018), Montr\'eal, Canada

Access Paper or Ask Questions

TopRank: A practical algorithm for online stochastic ranking

Jun 06, 2018
Tor Lattimore, Branislav Kveton, Shuai Li, Csaba Szepesvari

Figure 1 for TopRank: A practical algorithm for online stochastic ranking

Figure 2 for TopRank: A practical algorithm for online stochastic ranking

Access Paper or Ask Questions

Cleaning up the neighborhood: A full classification for adversarial partial monitoring

May 23, 2018
Tor Lattimore, Csaba Szepesvari

Figure 1 for Cleaning up the neighborhood: A full classification for adversarial partial monitoring

Figure 2 for Cleaning up the neighborhood: A full classification for adversarial partial monitoring

* 24 pages

Access Paper or Ask Questions

Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning

Jan 02, 2018
Christoph Dann, Tor Lattimore, Emma Brunskill

Figure 1 for Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning

Figure 2 for Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning

Figure 3 for Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning

* appears in Neural Information Processing Systems 2017

Access Paper or Ask Questions