collaborators

5 papers

eess.SY2019

Inverse Dynamic Games Based on Maximum Entropy Inverse Reinforcement Learning

Jairo Inga, Esther Bischoff, Florian Köpf +1

We consider the inverse problem of dynamic games, where cost function parameters are sought which explain observed behavior of interacting players. Maximum entropy inverse reinforc…

cs.MA2019

Deep Decentralized Reinforcement Learning for Cooperative Control

Florian Köpf, Samuel Tesfazgi, Michael Flad +1

In order to collaborate efficiently with unknown partners in cooperative control settings, adaptation of the partners based on online experience is required. The rather general and…

eess.SY2019

Adaptive Dynamic Programming for Model-free Tracking of Trajectories with Time-varying Parameters

Florian Köpf, Simon Ramsteiner, Michael Flad +1

In order to autonomously learn to control unknown systems optimally w.r.t. an objective function, Adaptive Dynamic Programming (ADP) is well-suited to adapt controllers based on ex…

eess.SY2019

Partner Approximating Learners (PAL): Simulation-Accelerated Learning with Explicit Partner Modeling in Multi-Agent Domains

Florian Köpf, Alexander Nitsch, Michael Flad +1

Mixed cooperative-competitive control scenarios such as human-machine interaction with individual goals of the interacting partners are very challenging for reinforcement learning…

eess.SY2019

Adaptive Optimal Control for Reference Tracking Independent of Exo-System Dynamics

Florian Köpf, Johannes Westermann, Michael Flad +1

Model-free control based on the idea of Reinforcement Learning is a promising approach that has recently gained extensive attention. However, Reinforcement-Learning-based control m…