no code implementations • 29 Oct 2019 • Florian Köpf, Samuel Tesfazgi, Michael Flad, Sören Hohmann
In order to collaborate efficiently with unknown partners in cooperative control settings, adaptation of the partners based on online experience is required.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 16 Sep 2019 • Florian Köpf, Simon Ramsteiner, Michael Flad, Sören Hohmann
We conclude our paper with an example which demonstrates that our new method successfully learns the optimal tracking controller and outperforms existing approaches in terms of tracking error and cost.
no code implementations • 9 Sep 2019 • Florian Köpf, Alexander Nitsch, Michael Flad, Sören Hohmann
Mixed cooperative-competitive control scenarios such as human-machine interaction with individual goals of the interacting partners are very challenging for reinforcement learning agents.
no code implementations • 12 Jun 2019 • Florian Köpf, Johannes Westermann, Michael Flad, Sören Hohmann
This paper provides for the first time an adaptive optimal control method capable to track reference trajectories not being generated by a time-invariant exo-system.