Applying and augmenting deep reinforcement learning in serious games through interaction

Abstract

Serious games belong to the most important future e-learning trends and are frequently used in recruitment and training. Their development, however, is still a demanding and tedious process, especially when regarding reasonable non-player character behaviour. Serious games can generally profit from diverse, adaptive behaviour to increase learning effectiveness. Deep reinforcement learning has already shown considerable results in automatically generating successful AI behaviour, but its past applications were mainly focused on optimization and short-horizon games. To expand the underlying ideas to serious games, 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 establish a synergistic combination of experts and emergent cognitive systems to create adaptive and more human behaviour. We call this approach interactive deep reinforcement learning and point out important aspects regarding realization within a novel framework.