Betreuer: Mohammd Karam Daaboul
Forschungsgruppe: Angewandte Technisch-Kognitive Systeme
Partner: FZI Forschungszentrum Informatik
Beginn: 04. Mai 2021
Reinforcement Learning (RL) is a method of machine learning in which an agent learns a strategy through interactions with its environment that maximizes the rewards it receives from the environment. The agent is not given a policy but is guided only by positive and negative rewards and optimizes his behavior. In many real-world scenarios, an agent faces the challenges of sparse extrinsic rewards, learning from limited samples, and no violation of safety constraints. This thesis aims to research the area of safe RL and develop a method to deal with those three problems.
Ausschreibung: Download (pdf)