| CODE | IDG5313 | ||||||||||||
| TITLE | Frontiers in Artificial Intelligence and Games | ||||||||||||
| UM LEVEL | 05 - Postgraduate Modular Diploma or Degree Course | ||||||||||||
| MQF LEVEL | 7 | ||||||||||||
| ECTS CREDITS | 5 | ||||||||||||
| DEPARTMENT | Institute of Digital Games | ||||||||||||
| DESCRIPTION | Frontiers in Artificial Intelligence and Games covers the state-of-the-art in academic research and game industry practices when it comes to Artificial Intelligence algorithms and applications. The topics covered in this unit are broad, from computer vision and controllers to computational creativity and affective computing. The course follows a pedagogical approach which blends seminars and reading group formats, and aims to empower students to explore, search, and critically reflect on academic literature pertaining to topics of artificial intelligence and games. This student initiative will be assessed through student presentations and discussions during the unit and a written survey on a specific topic among those covered during class. Study-Unit Aims: - to disseminate cutting-edge research on artificial intelligence and games; - to solicit in-depth discussions between students and lecturers on the limitations and possible improvements beyond the state of the art; - to prompt knowledge synthesis and critical reflection from students; - to prepare students for a possible career in AI research (in industry or academia). Learning Outcomes: 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - identify different types of procedural content generation that take advantage of current research in evolutionary computation, reinforcement learning, and supervised learning; - analyse current processes for supervised learning in computer vision, applied to games, affect modelling, computer vision, and related domains; - realize the challenges in modeling affect in terms of human biases, instrument biases, or data processing biases; - follow current trends for agent control in games, with a focus on reinforcement learning solutions. 2. Skills: By the end of the study-unit the student will be able to: - read and critically reflect on academic papers on the above topics, including the most recent state of the art; - present and engage with an audience on academic topics related to the above; - perform bibliographic search, survey, synthesize and report on scientific domains around artificial intelligence and games. Main Text/s and any supplementary readings: - Georgios N. Yannakakis and Julian Togelius (2018). Artificial Intelligence and Games. Springer. - Ecoffet, A., Huizinga, J., Lehman, J. et al. First return, then explore. Nature 590, 580–586 (2021). https://doi.org/10.1038/s41586-020-03157-9. - Khalifa, A., Bontrager, P., Earle, S., & Julian, T. (2020). PCGRL: procedural content generation via reinforcement learning. Proceedings of the Sixteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-20), 16(1), 95-101. - Gravina, D., Khalifa A., Liapis, A., Togelius, J. & Yannakakis, G. N. (2019). Procedural content generation through quality-diversity. Proceedings of the IEEE Conference on Games, London. - Vapnik, V. & Vashist, A. (2009). A new learning paradigm: Learning using privileged information,” Neural networks, vol. 22, no. 5-6, pp. 544–557. - Makantasis, K., Liapis, A., & Yannakakis, G. N. (2021). The pixels and sounds of emotion : general-purpose representations of arousal in games. IEEE Transactions on Affective Computing. - Yannakakis, G. N., Cowie, R., & Busso, C. (2017). The ordinal nature of emotions. Seventh International Conference on Affective Computing and Intelligent Interaction (ACII) IEEE. Various online readings based on students' interests and recent advances in the state-of-the-art. |
||||||||||||
| ADDITIONAL NOTES | Pre-requisite Qualification: Experience in Computer Science and Artificial Intelligence Pre-requisite Study-Unit: IDG5631 Co-Requisite Study-Unit: IDG5159 |
||||||||||||
| STUDY-UNIT TYPE | Lecture and Seminar | ||||||||||||
| METHOD OF ASSESSMENT |
|
||||||||||||
| LECTURER/S | |||||||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2024/5. It may be subject to change in subsequent years. |
|||||||||||||