Matthias Weissenbacher PhD
Researcher in Reinforcement learning (RL) - Artificial Intelligence (AI) - Mathematical Phsyics
Research Mission
My research focus is on generalization in Reinforcement Learning. Currently I hold a Research Scientist position at the Center for Advanced Intelligence Project (AIP) at RIKEN. My main ambition is to evolve RL algorithms that are able to generalize to out-of-distribution data as well as new new tasks as well as strategies. My current focus is on "Simple Q-learning" , i.e. on deducing basic guiding principles to make RL less hyper-parameter sensitive.
CV
My background is in mathematical (quantum) physics with my Master at ETH Zurich and my PhD in String theory at the Max Planck Institute for Physics in Munich. During my first Postdoc at the University of Tokyo (Kavli IPMU) my research interests shifted towards the vibrant field of AI.
ICML 2024
Happy to announce our paper at ICML2024 in Vienna!
Workshop on ML and Brain-like Intelligence - AIP/Shanghai JTU
Generalisation in image-based RL
(Time-stamp : 1h:29min)
Workshop on LLMs
Happy to announce our tutorial workshop on LLMs!
The workshop was organised by me to provide a thorough introduction to LLMs
Call for Collaborations
These days we started working on Quantum Reinforcement learning as well as Collaborative Game theory in Meta RL.
Always happy to discuss!
