-
Local Differentially Private Regret Minimization in Reinforcement Learning
Reinforcement learning algorithms are widely used in domains where it is...
10/15/2020 ∙ by Evrard Garcelon, et al. ∙
0
∙
share
read it
-
Adversarial Attacks on Linear Contextual Bandits
Contextual bandit algorithms are applied in a wide range of domains, fro...
02/10/2020 ∙ by Evrard Garcelon, et al. ∙
0
∙
share
read it
-
Improved Algorithms for Conservative Exploration in Bandits
In many fields such as digital marketing, healthcare, finance, and robot...
02/08/2020 ∙ by Evrard Garcelon, et al. ∙
0
∙
share
read it
-
Conservative Exploration in Reinforcement Learning
While learning in an unknown Markov Decision Process (MDP), an agent sho...
02/08/2020 ∙ by Evrard Garcelon, et al. ∙
0
∙
share
read it
-
No-Regret Exploration in Goal-Oriented Reinforcement Learning
Many popular reinforcement learning problems (e.g., navigation in a maze...
12/07/2019 ∙ by Jean Tarbouriech, et al. ∙
0
∙
share
read it
-
Bandits with Side Observations: Bounded vs. Logarithmic Regret
We consider the classical stochastic multi-armed bandit but where, from ...
07/10/2018 ∙ by Rémy Degenne, et al. ∙
0
∙
share
read it
