@inproceedings{,
    author = {Dobrovsky, Aline; Borghoff, Uwe M.; Hofmann, Marko},
    title = {An Approach to Interactive Deep Reinforcement Learning for Serious Games},
    editor = {},
    booktitle = {2016 7th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)},
    series = {},
    journal = {},
    address = {},
    publisher = {IEEE},
    edition = {},
    year = {2016},
    isbn = {978-1-5090-2645-6 ; 978-1-5090-2644-9},
    volume = {},
    number =  {},
    pages = {85-90},
    url = {https://doi.org/10.1109/CogInfoCom.2016.7804530},
    doi = {10.1109/CogInfoCom.2016.7804530},
    keywords = {Cognitive Systems ; Deep Learn - ing ; Serious Games,—Interactive Reinforcement Learning},
    abstract = {Serious games receive increasing interest in the area of e-learning. Their development, however, is often still a demand- ing, specialized and arduous process, especially when regard- ing 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. Keywords—Interactive Reinforcement Learning; Deep Learn- ing; Serious Games; Cognitive Systems},
    note = {},
    institution = {Universität der Bundeswehr München, Fakultät für Informatik, INF 2 - Institut für Softwaretechnologie, Professur: Borghoff, Uwe M.},
    
    
}