- Publications
- Influence
Share This Author
Bandit Algorithms
- Tor Lattimore, Csaba Szepesvári
- Mathematics
- 4 July 2020
sets of environments and policies respectively and ` : E ×Π→ [0, 1] a bounded loss function. Given a policy π let `(π) = (`(ν1, π), . . . , `(νN , π)) be the loss vector resulting from policy π.…
Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning
- Christoph Dann, Tor Lattimore, Emma Brunskill
- Computer ScienceNIPS
- 1 March 2017
TLDR
Causal Bandits: Learning Good Interventions via Causal Inference
- Finnian Lattimore, Tor Lattimore, M. Reid
- Computer ScienceNIPS
- 10 June 2016
TLDR
The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits
- Tor Lattimore, Csaba Szepesvari
- Computer ScienceAISTATS
- 1 October 2016
TLDR
PAC Bounds for Discounted MDPs
- Tor Lattimore, Marcus Hutter
- Computer ScienceALT
- 17 February 2012
TLDR
Learning with Good Feature Representations in Bandits and in RL with a Generative Model
- Tor Lattimore, Csaba Szepesvari
- Computer ScienceICML
- 18 November 2019
TLDR
Conservative Bandits
- Yifan Wu, R. Shariff, Tor Lattimore, Csaba Szepesvari
- Computer ScienceICML
- 13 February 2016
We study a novel multi-armed bandit problem that models the challenge faced by a company wishing to explore new strategies to maximize revenue whilst simultaneously maintaining their revenue above a…
Degenerate Feedback Loops in Recommender Systems
- Ray Jiang, S. Chiappa, Tor Lattimore, A. György, Pushmeet Kohli
- Computer ScienceAIES
- 27 January 2019
TLDR
Model Selection in Contextual Stochastic Bandit Problems
- Aldo Pacchiano, My Phan, Csaba Szepesvari
- Computer ScienceNeurIPS
- 3 March 2020
TLDR
TopRank: A practical algorithm for online stochastic ranking
- Tor Lattimore, B. Kveton, Shuai Li, Csaba Szepesvari
- Computer ScienceNeurIPS
- 6 June 2018
TLDR
...
...