Reinforcement Learning describes the situation of a machine learning system, where the only training signal provided by the environment is that of success or failure of the agent, after the system has acted over a sequence of decision cycles. This learning problem can be formulated as a Markov Decision Process (MDP) within the framework of dynamic programming.

Within our soccer simulation project FRA-UNIted, one of our main motivations has been to investigate reinforcement learning (RL) methods in a complex domain like robotic soccer, and to develop new variants and practical algorithmus. In that domain, we consider it particularly important to not only demonstrate the basic and principal feasibility of RL for a specific problem, but to actually apply learned behaviors in our competition team.