Reinforcement Learning Summer School

June 26th to July 5th, 2023, Barcelona

Program

Week 1:

26/6
MONDAY
27/6
TUESDAY
28/6
WEDNESDAY
29/6
THURSDAY
30/6
FRIDAY
9:30-11:00 AM MDPs and Dynamic Programming
Bruno Scherrer
Temporal Difference Methods
Herke van Hoof
Hierarchical RL
Anders Jonsson
Concentration Inequalities Contextual Bandits
Claire Vernade
11:00-11:15 AM Coffee break
11:15-12:45 PM From MDPs to RL Function Approximation (Neural Networks)
Niao He
Policy Gradient Methods
Gerhard Neumann
Stochastic Bandits
Emilie Kaufmann
Exploration in RL
Alessandro Lazaric
12:45-2:45 PM Lunch break
2:45-4:15 PM Practical Session DQN Tutorial
Antonin Raffin
Actor-Critic Tutorial
Vincent Moens
MCTS Tutorial
Tor Lattimore
Practical Session
4:15-4:30 PM Coffee break
4:30-6:00 PM Practical Session DQN Tutorial
Antonin Raffin
Actor-Critic Tutorial
Vincent Moens
MCTS Tutorial
Tor Lattimore
Poster Session

Week 2:

3/7
MONDAY
4/7
TUESDAY
5/7
WEDNESDAY
9:30-11:00 AM Regularization in RL
Matthieu Geist
Representation Learning and RL
Matteo Pirotta
Neuroscience
Daniel McNamee
11:00-11:15 AM Coffee break
11:15-12:45 PM Primal-Dual Methods
Gergeley Neu
Safe RL
Felix Berkenhamp
Symmetries in RL
Elise van der Pol
12:45-2:45 PM Lunch break
2:45-4:15 PM Practical Session Model-based RL
Andreas Krause
TBD
4:15-4:30 PM Coffee break
4:30-6:00 PM Practical Session Practical Session Final Quizz