activity
20122026
most citedCombinatorial Bandits Revisited

118 citations · 405 across the 29 of their papers we have counts for

collaborators

31 papers

cs.NI2026

Exponential Backoff: Meta-Stability and Implicit Admission Control

Richard Combes, Fabien Mathieu, Thomas Bonald

We analyze exponential backoff, an algorithm used to share a single communication channel in a distributed manner between several users, in a similar way as many networking standar…

stat.ML2021★ 5 cited

Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information

Wei Huang, Richard Combes, Cindy Trinh

We propose a novel algorithm for multi-player multi-armed bandits without collision sensing information. Our algorithm circumvents two problems shared by all state-of-the-art algor…

cs.LG2021★ 1 cited

A High Performance, Low Complexity Algorithm for Multi-Player Bandits Without Collision Sensing Information

Cindy Trinh, Richard Combes

Motivated by applications in cognitive radio networks, we consider the decentralized multi-player multi-armed bandit problem, without collision nor sensing information. We propose…

stat.ML2021★ 2 cited

Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time

Thibaut Cuvelier, Richard Combes, Eric Gourdin

We consider combinatorial semi-bandits with uncorrelated Gaussian rewards. In this article, we propose the first method, to the best of our knowledge, that enables to compute the s…

stat.ML2021★ 1 cited

On the Suboptimality of Thompson Sampling in High Dimensions

Raymond Zhang, Richard Combes

In this paper we consider Thompson Sampling (TS) for combinatorial semi-bandits. We demonstrate that, perhaps surprisingly, TS is sub-optimal for this problem in the sense that its…

cs.LO2020

Solving Random Parity Games in Polynomial Time

Richard Combes, Mikael Touati

We consider the problem of solving random parity games. We prove that parity games exibit a phase transition threshold above , so that when the degree of the graph that define…