|
Evrard Garcelon
I am a 3rd year PhD student at FAIR Paris and CREST, ENSAE.
I am co-advised by Matteo Pirotta and Vianney Perchet. Contact: evrard dot garcelon at gmail dot com .
|
|
Research
My main research interest is Reinforcement Learning (RL), in particular in exploration under the constraints of privacy, security or performance.
|
|
Publications
- Bandits with Side Observations: Bounded vs. Logarithmic Regret
Remy Degenne, Evrard Garcelon, Vianney Perchet
UAI 2018
- Adversarial Attacks on Linear Contextual Bandits
Evrard Garcelon*, Baptiste Roziere*, Laurent Meunier*, Jean Tarbouriech , Olivier Teytaud, Alessandro Lazaric, Matteo Pirotta
NeurIPS 2020
- No-Regret Exploration in Goal-Oriented Reinforcement Learning
Jean Tarbouriech, Evrard Garcelon, Michal Valko, Matteo Pirotta, Alessandro Lazaric
ICML 2020
- Improved Algorithms for Conservative Exploration in Bandits
Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta
AAAI 2020
- Conservative Exploration in Reinforcement Learning
Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta
AISTATS 2020
- Local Differential Privacy for Regret Minimization in Reinforcement Learning
Evrard Garcelon, Vianney Perchet, Ciara Pike-Burke, Matteo Pirotta
NeurIPS 2021
- Top Ranking for Multi-Armed Bandit with Noisy Evaluations
Evrard Garcelon, Vashist Avadhanula, Alessandro Lazaric, Matteo Pirotta
AISTATS 2022
- Privacy Amplification via Shuffling for Linear Contextual Bandits
Evrard Garcelon, Kamalika Chaudhuri, Vianney Perchet, Matteo Pirotta
ALT 2022
- Homomorphically Encrypted Linear Contextual Bandit
Evrard Garcelon, Vianney Perchet, Matteo Pirotta
AISTATS 2022
- A Unified Framework for Conservative Exploration
Yunchang Yang, Tianhao Wu, Han Zhong, Evrard Garcelon, Matteo Pirotta, Alessandro Lazaric, Liwei Wang, Simon S Du
ICLR 2022
|
|