4 papers
The Bias of Nonlinear Two-Time-scale Stochastic Approximation under Constant Step-Sizes
Djamel Rassem Lamouri, Dorian Baudry, Nicolas Gast
Two-timescale stochastic approximation (TTSA) is a fundamental tool for analyzing coupled iterative algorithms in reinforcement learning, optimization, and stochastic control. Howe…
A Perturbation Approach to Unconstrained Linear Bandits
Andrew Jacobsen, Dorian Baudry, Shinji Ito +1
We revisit the standard perturbation-based approach of Abernethy et al. (2008) in the context of unconstrained Bandit Linear Optimization (uBLO). We show the surprising result that…
Best-of-Both Worlds for linear contextual bandits with paid observations
Nathan Boyer, Dorian Baudry, Patrick Rebeschini
We study linear contextual bandits with paid observations, where at each round the learner observes a context, selects an action, and may pay a fixed cost to observe feedback from…
Non-stationary Bandit Convex Optimization: A Comprehensive Study
Xiaoqi Liu, Dorian Baudry, Julian Zimmert +2
Bandit Convex Optimization is a fundamental class of sequential decision-making problems, where the learner selects actions from a continuous domain and observes a loss (but not it…