Publications (38)
Refined Lower Bounds for Adversarial Bandits
Sébastien Gerchinovitz, Tor Lattimore
Thompson Sampling is Asymptotically Optimal in General Environments
Jan Leike, Tor Lattimore, Laurent Orseau +1
On First-Order Bounds, Variance and Gap-Dependent Bounds for Adversarial Bandits
Roman Pogodin, Tor Lattimore
Online Learning to Rank with Features
Shuai Li, Tor Lattimore, Csaba Szepesvári
BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback
Chang Li, Branislav Kveton, Tor Lattimore +4
Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits
Tor Lattimore
Cleaning up the neighborhood: A full classification for adversarial partial monitoring
Tor Lattimore, Csaba Szepesvari
Optimal Resource Allocation with Semi-Bandit Feedback
Tor Lattimore, Koby Crammer, Csaba Szepesvári
Free Lunch for Optimisation under the Universal Distribution
Tom Everitt, Tor Lattimore, Marcus Hutter
Concentration and Confidence for Discrete Bayesian Sequence Predictors
Tor Lattimore, Marcus Hutter, Peter Sunehag
Bounded Regret for Finite-Armed Structured Bandits
Tor Lattimore, Remi Munos
Single-Agent Policy Tree Search With Guarantees
Laurent Orseau, Levi H. S. Lelis, Tor Lattimore +1
Iterative Budgeted Exponential Search
Malte Helmert, Tor Lattimore, Levi H. S. Lelis +2
The paper proposes a new iterative framework that controls expansion budgets and solution cost limits, producing graph and tree search algorithms with O(n log C) expansions, improv…
Universal Prediction of Selected Bits
Tor Lattimore, Marcus Hutter, Vaibhav Gavane
Zooming Cautiously: Linear-Memory Heuristic Search With Node Expansion Guarantees
Laurent Orseau, Levi H. S. Lelis, Tor Lattimore
Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities
Ruitong Huang, Tor Lattimore, András György +1
Soft-Bayes: Prod for Mixtures of Experts with Log-Loss
Laurent Orseau, Tor Lattimore, Shane Legg
Asymptotics of Continuous Bayes for Non-i.i.d. Sources
Tor Lattimore, Marcus Hutter
Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning
Christoph Dann, Tor Lattimore, Emma Brunskill
The Sample-Complexity of General Reinforcement Learning
Tor Lattimore, Marcus Hutter, Peter Sunehag
Conservative Bandits
Yifan Wu, Roshan Shariff, Tor Lattimore +1
Causal Bandits: Learning Good Interventions via Causal Inference
Finnian Lattimore, Tor Lattimore, Mark D. Reid
Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits
Branislav Kveton, Csaba Szepesvari, Sharan Vaswani +3
PAC Bounds for Discounted MDPs
Tor Lattimore, Marcus Hutter
Online Learning with Gated Linear Networks
Joel Veness, Tor Lattimore, Avishkar Bhoopchand +3
TopRank: A practical algorithm for online stochastic ranking
Tor Lattimore, Branislav Kveton, Shuai Li +1
Asymptotically Optimal Agents
Tor Lattimore, Marcus Hutter
The Pareto Regret Frontier for Bandits
Tor Lattimore
Degenerate Feedback Loops in Recommender Systems
Ray Jiang, Silvia Chiappa, Tor Lattimore +2
A Geometric Perspective on Optimal Representations for Reinforcement Learning
Marc G. Bellemare, Will Dabney, Robert Dadashi +6
Regret Analysis of the Anytime Optimally Confident UCB Algorithm
Tor Lattimore
No Free Lunch versus Occam's Razor in Supervised Learning
Tor Lattimore, Marcus Hutter
The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits
Tor Lattimore, Csaba Szepesvari
An Information-Theoretic Approach to Minimax Regret in Partial Monitoring
Tor Lattimore, Csaba Szepesvari
A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis
Tor Lattimore
Connections Between Mirror Descent, Thompson Sampling and the Information Ratio
Julian Zimmert, Tor Lattimore
On Explore-Then-Commit Strategies
Aurélien Garivier, Emilie Kaufmann, Tor Lattimore
Optimally Confident UCB: Improved Regret for Finite-Armed Bandits
Tor Lattimore