An approach to interactive deep reinforcement learning for serious games
Aline Dobrovsky, Uwe M. Borghoff, Marko A. Hofmann · 2016
Serious games receive increasing interest in the area of e-learning. Their development, however, is often still a demanding, specialized and arduous process, especially when regarding reasonable non-player character behaviour. Reinforcement learning and, since recently, also deep reinforcement learning have proven to automatically generate successful AI behaviour to a certain degree. These methods are computationally expensive and hardly scalable to various complex serious game scenarios. For this reason, we introduce a new approach of augmenting the application of deep reinforcement learning methods by interactively making use of domain experts' knowledge to guide the learning process. Thereby, we aim to create a synergistic combination of experts and emergent cognitive systems. We call this approach interactive deep reinforcement learning and point out important aspects regarding realization within a framework.