298 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université de LilleFR364 papers
- Centre National de la Recherche ScientifiqueFR257 papers
- École Centrale de LilleFR212 papers
- Centre de Recherche en InformatiqueFR203 papers
- Université Paris-SaclayFR74 papers
- Institut d'Astrophysique SpatialeFR64 papers
- Sorbonne UniversitéFR59 papers
- Institut de Recherche en Astrophysique et PlanétologieFR58 papers
- Université Paris CitéFR57 papers
- Université Paris Sciences et LettresFR53 papers
- Ludwig-Maximilians-Universität MünchenDE52 papers
- CEA Paris-SaclayFR51 papers
8 papers · 2 filters
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…
Model-Based Reinforcement Learning Exploiting State-Action Equivalence
Mahsa Asadi, Mohammad Sadegh Talebi, Hippolyte Bourel +1
Leveraging an equivalence property in the state-space of a Markov Decision Process (MDP) has been investigated in several studies. This paper studies equivalence structure in the r…
HIGhER : Improving instruction following with Hindsight Generation for Experience Replay
Geoffrey Cideron, Mathieu Seurin, Florian Strub +1
Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may…
MERL: Multi-Head Reinforcement Learning
Yannis Flet-Berliac, Philippe Preux
A common challenge in reinforcement learning is how to convert the agent's interactions with an environment into fast and robust learning. For instance, earlier work makes use of d…
SPOCC: Scalable POssibilistic Classifier Combination -- toward robust aggregation of classifiers
Mahmoud Albardan, John Klein, Olivier Colot
We investigate a problem in which each member of a group of learners is trained separately to solve the same classification task. Each learner has access to a training dataset (pos…
Learning Multiple Markov Chains via Adaptive Allocation
Mohammad Sadegh Talebi, Odalric-Ambrym Maillard
We study the problem of learning the transition matrices of a set of Markov chains from a single stream of observations on each chain. We assume that the Markov chains are ergodic…
Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL
Yannis Flet-Berliac, Philippe Preux
In reinforcement learning, policy gradient algorithms optimize the policy directly and rely on sampling efficiently an environment. Nevertheless, while most sampling procedures are…
Budgeted Reinforcement Learning in Continuous State Space
Nicolas Carrara, Edouard Leurent, Romain Laroche +3
A Budgeted Markov Decision Process (BMDP) is an extension of a Markov Decision Process to critical applications requiring safety constraints. It relies on a notion of risk implemen…