6 papers
Local Differential Privacy for Regret Minimization in Reinforcement Learning
Evrard Garcelon, Vianney Perchet, Ciara Pike-Burke +1
Reinforcement learning algorithms are widely used in domains where it is desirable to provide a personalized service. In these domains it is common that user data contains sensitiv…
Improved Algorithms for Conservative Exploration in Bandits
Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric +1
In many fields such as digital marketing, healthcare, finance, and robotics, it is common to have a well-tested and reliable baseline policy running in production (e.g., a recommen…
Adversarial Attacks on Linear Contextual Bandits
Evrard Garcelon, Baptiste Roziere, Laurent Meunier +4
Contextual bandit algorithms are applied in a wide range of domains, from advertising to recommender systems, from clinical trials to education. In many of these domains, malicious…
Conservative Exploration in Reinforcement Learning
Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric +1
While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowled…
No-Regret Exploration in Goal-Oriented Reinforcement Learning
Jean Tarbouriech, Evrard Garcelon, Michal Valko +2
Many popular reinforcement learning problems (e.g., navigation in a maze, some Atari games, mountain car) are instances of the episodic setting under its stochastic shortest path (…
Bandits with Side Observations: Bounded vs. Logarithmic Regret
Rémy Degenne, Evrard Garcelon, Vianney Perchet
We consider the classical stochastic multi-armed bandit but where, from time to time and roughly with frequency , an extra observation is gathered by the agent for free. We prov…