Connectionists: PhD Position on DRL for robot locomotion

[malte.schilling at uni-muenster.de]

There is a PhD position open in the Autonomous Intelligent Systems group at the University of Münster.

The focus of the position will be on Deep Reinforcement Learning for the control of locomotion in robots. In particular, we are aiming to develop biologically-inspired principles that enable efficient learning mechanisms for adaptive behaviour. This position will focus on a model-based learning and planning architecture for the control of a robot based on principles such as decentralization and hierarchical organization. This architecture shall be applied to one of our robots, e.g., the Unitree Go1, in multiple and increasingly more difficult tasks that require the transfer of learning. One possible direction could be to extend such a DRL-based approach into a multi-agent setting which requires  dealing with other agents and making the decision-making transparent in a cooperative task, e.g., through transferring methods from XAI to DRL (for more information, get in contact with us). 
This position is tied to working towards a doctorate and you will have the opportunity to work closely together with another position focused on learning from predictive models using graph neural networks.

For more information, get in contact with us and see: https://www.uni-muenster.de/Rektorat/Stellen/ausschreibungen/st_20233103_sk5.html

Applications of interested computer scientists and machine learners are welcome!
Regards

 Malte Schilling

--
Prof. Dr. Malte Schilling
Autonomous Intelligent Systems Group, University of Münster
Computer Science Department, FB 10
Einsteinstr. 62, D-48149 Münster, Germany
Tel: +49-251-8333804
malte.schilling at uni-muenster.de