Offline Reinforcement Learning, also das Erlernen einer Policy auf Basis eines statischen Datensatzes ohne Interaktion mit der Umwelt, verspricht neue Anwendungsfelder zu erschließen und besser zu skalieren als gewöhnliche Reinforcement Learning …
Robot arms are used in a wide variety of tasks. As part of the Test Area Intelligent Quartier Mobility project, a Husky robot with mounted UR5 should perform a simple task on the HAW campus.
Das Ziel dieser Arbeit ist es zu zeigen, dass sich die vorgestellte Simulationsumgebung zur Umsetzung und Entwicklung eines selbstlernenden Reglers für autonome Wasserfahrzeuge eignet. Als Anwendungsgebiet wird ein bereits bestehendes Miniaturschiff …
Reinforcement learning allows a self-learning agent to stabilize an unmanned aerial vehicle in uncontrolled flight states. To achieve this, a deep deterministic policy gradient algorithm is applied. Through extensions like experience replay memory, …
One of the most difficult challenges in reinforcement learning is the continuous control of systems in a continuous state and action space. This papers goal is to design and implement a reinforcement learning based airplane autopilot that controls an …
This work presents an approach for learning secure step positions, with the objective that the four-legged robot AMEE can safely walk in rough terrain. The autonomous task to be mastered is to identify features of the surrounding area. The …
We develop a theoretical framework for the problem of learning optimal control. We consider a discounted infinite horizon deterministic control problem in the reinforcement learning context. The main objective is to approximate the optimal value …