157 citations · 713 across the 56 of their papers we have counts for
6 papers · 1 filter
Sparse Optimistic Information Directed Sampling
Ludovic Schwartz, Hamish Flynn, Gergely Neu
Many high-dimensional online decision-making problems can be modeled as stochastic sparse linear bandits. Most existing algorithms are designed to achieve optimal worst-case regret…
Linear Bandits with Non-i.i.d. Noise
Baptiste Abélès, Eugenio Clerico, Hamish Flynn +1
We study the linear stochastic bandit problem, relaxing the standard i.i.d. assumption on the observation noise. As an alternative to this restrictive assumption, we allow the nois…
Distances for Markov chains from sample streams
Sergio Calo, Anders Jonsson, Gergely Neu +2
Bisimulation metrics are powerful tools for measuring similarities between stochastic processes, and specifically Markov chains. Recent advances have uncovered that bisimulation me…
Inverse Q-Learning Done Right: Offline Imitation Learning in -Realizable MDPs
Antoine Moulin, Gergely Neu, Luca Viano
We study the problem of offline imitation learning in Markov decision processes (MDPs), where the goal is to learn a well-performing policy given a dataset of state-action pairs ge…
Confidence Sequences for Generalized Linear Models via Regret Analysis
Eugenio Clerico, Hamish Flynn, Wojciech Kotłowski +1
We develop a methodology for constructing confidence sets for parameters of statistical models via a reduction to sequential prediction. Our key observation is that for any general…
Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning
Antoine Moulin, Gergely Neu, Luca Viano
We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm ach…