Half-Day Wokshop at ECML PKDD

1st Scaling-Up Reinforcement Learning (SURL) Workshop

Program as pdf



Time Program
8h00 – 8h55 Registration
Session 1
8h55 – 9h00 Opening
9h00 - 9h20 Case-based Policy Inference for Transfer in Reinforcement Learning
R. Glatt, F. L. Silva and A. H. R. Costa
9h20 – 9h40 Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
J. Foerster, N. Nardelli, G. Farquhar, T. Afouras, P. Torr, P. Kohli and S. Whiteson
9h40 – 10h00 Constrained Bayesian Reinforcement Learning via Approximate Linear Programming - slides
J. Lee, Y. Jang, P. Poupart and K. Kim
10h00 – 11h40 Invited Talk:Scaling up RL with Offline Task Hierarchies
Devin Schwab (Carnegie Mellon University)
11h40 – 12h00 Coffee break
Session 2
11h00 – 11h20 Automatic Object-Oriented Curriculum Generation for Reinforcement Learning
F. L. Silva and A. H. R. Costa
11h20 – 11h40 Count-Based Exploration in Feature Space for Reinforcement Learning
J. Martin, S. Narayanan S., T. Everitt and M. Hutter
11h40 – 12h00 Learning Multimodal Transition Dynamics for Model-Based Reinforcement Learning - slides
T. M. Moerland, J. Broekens and C. M. Jonker
12h00 – 12h40 Invited Talk:Scaling Up Policy Search Methods for Robotics
Herke van Hoof (McGill University)
12h40 - 12h45 Closing / Community Meeting / Integration