3.4k citations · 4.9k across the 135 of their papers we have counts for
8 papers · 1 filter
No-Regret Exploration in Goal-Oriented Reinforcement Learning
Jean Tarbouriech, Evrard Garcelon, Michal Valko +2
Many popular reinforcement learning problems (e.g., navigation in a maze, some Atari games, mountain car) are instances of the episodic setting under its stochastic shortest path (…
Fixed-Confidence Guarantees for Bayesian Best-Arm Identification
Xuedong Shang, Rianne de Heide, Emilie Kaufmann +2
We investigate and provide new insights on the sampling rule called Top-Two Thompson Sampling (TTTS). In particular, we justify its use for fixed-confidence best-arm identification…
Derivative-Free & Order-Robust Optimisation
Victor Gabillon, Rasul Tutunov, Michal Valko +1
In this paper, we formalise order-robust optimisation as an instance of online learning minimising simple regret, and propose Vroom, a zero'th order optimisation algorithm capable…
Multiagent Evaluation under Incomplete Information
Mark Rowland, Shayegan Omidshafiei, Karl Tuyls +4
This paper investigates the evaluation of learned multiagent strategies in the incomplete information setting, which plays a critical role in ranking and training of agents. Tradit…
Exact sampling of determinantal point processes with sublinear time preprocessing
Michał Dereziński, Daniele Calandriello, Michal Valko
We study the complexity of sampling from a distribution over all index subsets of the set with the probability of a subset proportional to the determinant of the…
Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret
Daniele Calandriello, Luigi Carratino, Alessandro Lazaric +2
Gaussian processes (GP) are a well studied Bayesian approach for the optimization of black-box functions. Despite their effectiveness in simple problems, GP-based algorithms hardly…
Exploiting Structure of Uncertainty for Efficient Matroid Semi-Bandits
Pierre Perrault, Vianney Perchet, Michal Valko
We improve the efficiency of algorithms for stochastic \emph{combinatorial semi-bandits}. In most interesting problems, state-of-the-art algorithms take advantage of structural pro…
Optimistic optimization of a Brownian
Jean-Bastien Grill, Michal Valko, Rémi Munos
We address the problem of optimizing a Brownian motion. We consider a (random) realization of a Brownian motion with input space in . Given , our goal is to return an…