Picture for Tor Lattimore

Tor Lattimore

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

Add code
Jan 08, 2019
Viaarxiv icon

Single-Agent Policy Tree Search With Guarantees

Add code
Nov 28, 2018
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
Viaarxiv icon

Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits

Add code
Nov 13, 2018
Figure 1 for Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits
Figure 2 for Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits
Viaarxiv icon

BubbleRank: Safe Online Learning to Rerank

Add code
Jun 15, 2018
Figure 1 for BubbleRank: Safe Online Learning to Rerank
Figure 2 for BubbleRank: Safe Online Learning to Rerank
Figure 3 for BubbleRank: Safe Online Learning to Rerank
Viaarxiv icon

TopRank: A practical algorithm for online stochastic ranking

Add code
Jun 06, 2018
Figure 1 for TopRank: A practical algorithm for online stochastic ranking
Figure 2 for TopRank: A practical algorithm for online stochastic ranking
Viaarxiv icon

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

Add code
May 23, 2018
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
Viaarxiv icon

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

Add code
Jan 02, 2018
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
Viaarxiv icon

Online Learning with Gated Linear Networks

Add code
Dec 05, 2017
Figure 1 for Online Learning with Gated Linear Networks
Figure 2 for Online Learning with Gated Linear Networks
Figure 3 for Online Learning with Gated Linear Networks
Figure 4 for Online Learning with Gated Linear Networks
Viaarxiv icon

A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis

Add code
Mar 27, 2017
Figure 1 for A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis
Viaarxiv icon

Refined Lower Bounds for Adversarial Bandits

Add code
Feb 27, 2017
Viaarxiv icon