56 citations · 200 across the 32 of their papers we have counts for
36 papers
Foundations of Reinforcement Learning and Control:Connections and New Perspectives
Claire Vernade, Onno Eberhard, Martha White +4
Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using feedback. While both fields…
To Retain or to Adapt? Generalizing Continual Learning
Giulia Lanzillotta, Mandana Samiei, Doina Precup +2
The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting. This objective rests on an often unstated assumption: that a lifelong…
Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation
Ziyad Sheebaelhamd, Luca Viano, Volkan Cevher +1
This work investigates multi-objective imitation learning: the problem of recovering policies that lie on the Pareto front given demonstrations from multiple Pareto-optimal experts…
Tight Sample Complexity Bounds for Entropic Best Policy Identification
Amer Essakine, Claire Vernade
We study best-policy identification for finite-horizon risk-sensitive reinforcement learning under the entropic risk measure. Recent work established a constant gap in the exponent…
Commit to the Bit: Reactive Reinforcement Learning Done Right
Onno Eberhard, Claire Vernade, Michael Muehlebach
Reinforcement learning algorithms are commonly analyzed (and designed) under the Markov assumption. This is unrealistic, as most environments encountered in practice are either par…
Non-Stationary Lipschitz Bandits
Nicolas Nguyen, Solenne Gaucher, Claire Vernade
We study the problem of non-stationary Lipschitz bandits, where the number of actions is infinite and the reward function, satisfying a Lipschitz assumption, can change arbitrarily…
Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning
Amir Rezaei Balef, Claire Vernade, Katharina Eggensperger
The Combined Algorithm Selection and Hyperparameter optimization (CASH) is a challenging resource allocation problem in the field of AutoML. We propose MaxUCB, a max k-armed bandit…
Clustered KL-barycenter design for policy evaluation
Simon Weissmann, Till Freihaut, Claire Vernade +2
In the context of stochastic bandit models, this article examines how to design sample-efficient behavior policies for the importance sampling evaluation of multiple target policie…
Partially Observable Reinforcement Learning with Memory Traces
Onno Eberhard, Michael Muehlebach, Claire Vernade
Partially observable environments present a considerable computational challenge in reinforcement learning due to the need to consider long histories. Learning with a finite window…
Quantization-Free Autoregressive Action Transformer
Ziyad Sheebaelhamd, Michael Tschannen, Michael Muehlebach +1
Current transformer-based imitation learning approaches introduce discrete action representations and train an autoregressive transformer decoder on the resulting latent code. Howe…
Efficient Risk-sensitive Planning via Entropic Risk Measures
Alexandre Marthe, Samuel Bounan, Aurélien Garivier +1
Risk-sensitive planning aims to identify policies maximizing some tail-focused metrics in Markov Decision Processes (MDPs). Such an optimization task can be very costly for the mos…
Variational Bayes Portfolio Construction
Nicolas Nguyen, James Ridgway, Claire Vernade
Portfolio construction is the science of balancing reward and risk; it is at the core of modern finance. In this paper, we tackle the question of optimal decision-making within a B…
Online Decision Deferral under Budget Constraints
Mirabel Reid, Tom Sühr, Claire Vernade +1
Machine Learning (ML) models are increasingly used to support or substitute decision making. In applications where skilled experts are a limited resource, it is crucial to reduce t…
A Pontryagin Perspective on Reinforcement Learning
Onno Eberhard, Claire Vernade, Michael Muehlebach
Reinforcement learning has traditionally focused on learning state-dependent policies to solve optimal control problems in a closed-loop fashion. In this work, we introduce the par…
Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits
Nicolas Nguyen, Imad Aouali, András György +1
We study the problem of Bayesian fixed-budget best-arm identification (BAI) in structured bandits. We propose an algorithm that uses fixed allocations based on the prior informatio…
Beyond Average Return in Markov Decision Processes
Alexandre Marthe, Aurélien Garivier, Claire Vernade
What are the functionals of the reward that can be computed and optimized exactly in Markov Decision Processes?In the finite-horizon, undiscounted setting, Dynamic Programming (DP)…
POMRL: No-Regret Learning-to-Plan with Increasing Horizons
Khimya Khetarpal, Claire Vernade, Brendan O'Donoghue +2
We study the problem of planning under model uncertainty in an online meta-reinforcement learning (RL) setting where an agent is presented with a sequence of related tasks with lim…
Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms
MohammadJavad Azizi, Thang Duong, Yasin Abbasi-Yadkori +3
We study a sequential decision problem where the learner faces a sequence of -armed bandit tasks. The task boundaries might be known (the bandit meta-learning setting), or unkno…
EigenGame Unloaded: When playing games is better than optimizing
Ian Gemp, Brian McWilliams, Claire Vernade +1
We build on the recently proposed EigenGame that views eigendecomposition as a competitive game. EigenGame's updates are biased if computed using minibatches of data, which hinders…
Asymptotically Optimal Information-Directed Sampling
Johannes Kirschner, Tor Lattimore, Claire Vernade +1
We introduce a simple and efficient algorithm for stochastic linear bandits with finitely many actions that is asymptotically optimal and (nearly) worst-case optimal in finite time…
The Elliptical Potential Lemma Revisited
Alexandra Carpentier, Claire Vernade, Yasin Abbasi-Yadkori
This note proposes a new proof and new perspectives on the so-called Elliptical Potential Lemma. This result is important in online learning, especially for linear stochastic bandi…
EigenGame: PCA as a Nash Equilibrium
Ian Gemp, Brian McWilliams, Claire Vernade +1
We present a novel view on principal component analysis (PCA) as a competitive game in which each approximate eigenvector is controlled by a player whose goal is to maximize their…
Stochastic bandits with arm-dependent delays
Anne Gael Manegueu, Claire Vernade, Alexandra Carpentier +1
Significant work has been recently dedicated to the stochastic delayed bandit setting because of its relevance in applications. The applicability of existing algorithms is however…
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting
Ilja Kuzborskij, Claire Vernade, András György +1
We consider off-policy evaluation in the contextual bandit setting for the purpose of obtaining a robust off-policy selection strategy, where the selection strategy is evaluated ba…