Reinforcement learning applications have evolved rapidly throughout the last decade.
Recently the DFKI successfully implemented a reinforcement learning (RL) algorithm that uses error potentials evoked by error recognition in the human brain for human robot interaction. The algorithm makes it possible to map gesture inputs to robotic actions using error potentials as feedback (reward in RL).
New situations in real world applications could make it necessary to adapt the approach.
The master thesis will focus on investigating approaches that make it possible to add gestures and actions, while retaining already learned knowledge. In addition, changing the meaning of a single gesture or completely relearning the gesture-action mapping are considered to be useful functions to be implemented. The developed algorithm is then to be validated through studies with a reasonable number of subjects.
