Agenda – Online learning

Back to event page…

Joining Instructions: Delegates should report to The Alan Turing Institute, first floor British Library, via the main library doors.

British Library
96 Euston Rd, London NW1 2DB, UK

10:00 – 10:25   Registration & Coffee

10:25 – 10:30   Welcome and Introduction

10:30 – 11:30   Bandit regret scaling with the effective loss range – Nicolò Cesa-Bianchi (Università degli Studi di Milano, Italy)

11:30 – 12:00   Coffee break

12:00 – 13:00   Sparsity, variance and curvature in multi-armed bandits – Sébastien Bubeck (Microsoft Research, USA)

13:00 – 14:00   Lunch

14:00 – 15:00   Online version of search problems – Vianney Perchet (ENS Paris-Saclay and Criteo, France)

15:00 – 15:30   Coffee break

15:30 – 16:30   On optimal strategies via random playouts and perturbations – Jacob Abernethy (Georgia Institute of Technology, USA)

16:30 – 17:30   Exploration in reinforcement learning: from tight regret analysis of finite MDPs to intrinsic motivation in deep RL – Rémi Munos and Mohammad Gheshlaghi Azar (DeepMind, UK)

17:30 – 19:00 Networking reception