Group formation
For the first week a brief history of the group formation, organization, and goals are needed to define the context. The alignment between the group interest and my personal interest in Artificial Intelligence and Machine Learning applied to game development the hardly connected to our initial value proposition.
Avoiding past mistakes (mine) we formed the group earlier (at the end of the past module, somewhere in May). The first interaction with Nural, which assumed the role team lead. In our first interaction, we set up a call and defined what would be the theme. The game structure, based on what I have done in the past, would be a 2D game. The theme would be correlated to AI/ML, this is a theme that I’m deeply interested in due to the intersection with my personal career and which I have a personal belief that is a breakthrough to the game design when fully adopted. After this first session everything went really well, the group formed itself by the invitation published in our Discord channel and forum.
The structure of the team is 2 developers, one UX expert, one artist, and one UX/Narrative/leader. The first action was the definition of golden ours and our sessions times besides the structure that we would follow in order to have a clear view of our progress.
First group session
We defined the adoption of Jira and Confluence as the main documentation and managing tool and to follow weekly sprints. Everything is available at: https://akanoodles.atlassian.net/wiki/home.
The general conclusion of this session was the definition of our golden hours or optimal time to schedule group sessions and the roles assumed by each member. Some of the structures of the projects started to be highlighted.
As I have some experience with SCRUM and use it in my daily life I assumed the role of Scrum master. I’ll focus in conduct the ceremonies and block removal, so everyone can work without problems.
Some of the technical specifications were highlighted like: the adoption of Unity and Artificial Intelligence application.
This was a good start, we had plenty of open questions, the interaction was nice in general and I got really excited to work with a group with a different mindset that I can find in my work.
Personal goals
Artificial Intelligence has been applied to the Game Industry and academically is agreed that it assumes three roles (Riedl and Zook, 2013):
- Artificial Intelligence as Actor: commonly represented by non-player characters (NPC) or Drama management
- Artificial Intelligence as Designer: often referred to as Procedural Generation Content (PGC), or a combination with adaptive forms of gameplay
- Artificial Intelligence as Producer: a more complex approach which an AI with access to a wealth data work with persistent games, game ecosystem, player communities and real-virtual world coupling.
Naturally I focused at the first role, AI as Actor due the relatively low levels of complexity and large amount of learning resource available. Moving toward this direction I’ll orient my first research on the basic tutorials to applied AI/ML algorithms to the Unity platform.
As a learner I’m interested in concrete applications and it will work as an requirement for my next activities.
References
6 Ways Machine Learning will be used in Game Development (no date) Logikk. Available at: https://www.logikk.com/articles/machine-learning-in-game-development/ (Accessed: 13 June 2021).
Chen, K. (2019) ‘Learning-Based Video Game Development in MLP@UoM: An Overview’, in 2019 International Conference on Electrical, Electronics and Information Engineering (ICEEIE). 2019 International Conference on Electrical, Electronics and Information Engineering (ICEEIE), pp. 1–6. doi: 10.1109/ICEEIE47180.2019.8981430.
Guzdial, M. and Riedl, M. (2018) ‘Automated Game Design via Conceptual Expansion’, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 14(1). Available at: https://ojs.aaai.org/index.php/AIIDE/article/view/13022 (Accessed: 13 June 2021).
Rieder, B. (no date) ‘Using Procedural Content Generation via Machine Learning as a Game Mechanic’, p. 108.Riedl, M. O. and Zook, A. (2013) ‘AI for game production’, in 2013 IEEE Conference on Computational Inteligence in Games (CIG). 2013 IEEE Conference on Computational Inteligence in Games (CIG), pp. 1–8. doi: 10.1109/CIG.2013.6633663.
Sarkar, A. and Cooper, S. (2020) ‘Towards Game Design via Creative Machine Learning (GDCML)’, in 2020 IEEE Conference on Games (CoG). 2020 IEEE Conference on Games (CoG), pp. 744–751. doi: 10.1109/CoG47356.2020.9231927.
Lucas Souza 