Recent & Upcoming Talks

2022

Near instance-optimal PAC Reinforcement Learning in deterministic MDPs

My talk at the JDS(French Statistical Days) 2022.

Jun 16, 2022 12:00 AM Université Lyon 1

Near instance-optimal PAC Reinforcement Learning in deterministic MDPs

2021

Adaptive Sampling for best policy Identification in MDPs

My talk at the RL Theory Seminar 2021.

May 11, 2021 12:00 AM Virtual

Adaptive Sampling for best policy Identification in MDPs