Beginning of October, we co-organized the ELLIS coordinator’s meeting in Delft. Here is a summary: https://ellis.eu/news/strengthening-collaboration-across-europe-the-2nd-ellis-coordinators-retreat
Author: frans
Appointed Full Professor ‘Interactive Learning & Decision Making’
Happy to announce that the executive board of TU Delft has appointed me to Full Professor! Some more details here.
TMLR accepted: Bayesian RL with Abstraction
Congrats to Rolf and all the other coathors on getting a paper accepted at TMLR! The paper shows how the technique for doing Bayesian RL in factored POMDPs (yes, we retain beliefs over the causal working of the world!) developed in earlier work can be combined with abstraction methods. More info here.
Outstanding Paper Award on Scientific Understanding @ RLC 2024
Very proud of my (graduated) student Miguel. His persistence made the difference for this final part of his PhD thesis!
Looking for PhD student
With Julia Olkhovskaia as the main supervisor, I am looking for a (fully paid) PhD student.
See details on my vacancy page.
Wanted: assist./assoc. professor in causal reinforcement learning
At TU Delft, we are recruiting an assist/assoc. professor in causal reinforcement learning.
More info here.
Comments for Volkskrant
For the Volkskrant, I commented on the Stratego article in science. Read it here.
Berkeley MARL Seminar talk online
The talk that I gave for the Berkeley MARL seminar can now be seen on youtube.
It gives an introduction to ideas of influence-based abstraction, focusing also on the inspirations from multiagent planning, as well as implications for future MARL.
DIALS accepted to NeurIPS’22
Our paper Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems was accepted to NeurIPS! It shows how influence-based abstraction can be used to parallelize and thus speed up multiagent reinforcement learning, while stabilizing the learning at the same time.
2 ILDM papers to appear at ICML
Our group will be presenting 2 papers at ICML’22:
On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games
Come find us at ICML, or reach out over email!