1 citations · 3 across the 3 of their papers we have counts for
5 papers
Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
Bastien Dubail, Stefan Stojanovic, Alexandre Proutière
Low-rank structure is a common implicit assumption in many modern reinforcement learning (RL) algorithms. For instance, reward-free and goal-conditioned RL methods often presume th…
Cutoff for mixtures of permuted Markov chains: general case
Bastien Dubail
We investigate the mixing properties of a finite Markov chain in random environment defined as a mixture of a deterministic chain and a chain whose state space has been permuted un…
Cutoff for mixtures of permuted Markov chains: reversible case
Bastien Dubail
We investigate the mixing properties of a model of reversible Markov chains in random environment, which notably contains the simple random walk on the superposition of a determini…
Accelerating Abelian Random Walks with Hyperbolic Dynamics
Bastien Dubail, Laurent Massoulié
Given integers , we consider affine random walks on torii defined as , where $A \in \mathrm{…
Markovian linearization of random walks on groups
Charles Bordenave, Bastien Dubail
In operator algebra, the linearization trick is a technique that reduces the study of a non-commutative polynomial evaluated at elements of an algebra A to the study of a polynomia…