Fabio Zambetta

Dr Fabio Zambetta is the Director of the Artificial Intelligence for Game Design node and also a Senior Lecturer in the School of CS&IT, RMIT University.

As Coordinator for the Games & Graphics Programming degree (BP215) Fabio teaches units devoted to game development, advanced games programming an AI in (computer) games. He has been instrumental in setting up the core studio-based units in the Games & Graphics Programming as well as the Games Design degrees. As such, Fabio has about 10 years experience in delivering studio-based introductory classes in a multi disciplinary environment and has taught specialist units in games AI, machine learning, computer graphics and virtual reality over the last 15 years.

Fabio’s research interests focus on AI in computer games, Procedural Content Generation, Interactive Narrative and the use of MachineLearning in those. He is also interested in Computer Graphics, Virtual Reality and Natural User Interfaces and he is leading an ARC Linkage project on the use of those technologies in Village Roadshow’s theme parks on the Gold Coast.

As a keen programmer he tends to do a fair amount of work in C/C++, C# and Python. He uses Matlab & Octave for prototyping; middleware such as Unity3D, Unreal Engine 4 and The AI Sandbox. In the past, Fabio has also used (and taught) Unreal Engine 2.X & 3.X, Neverwinter Night’s Aurora & Electron engines and Quake/Doom engines.

Capabilities

Machine Learning
Robotics, Adaptive Agents
Virtual Reality
Augmented Reality
Mixed Reality
Procedural Content Generation
Interactive Narrative
Automated Games Design
Decision support systems
Data Analytics
Gamification
Dynamic Systems
Game Theory
Mathematical Modelling
Statistical Inference

Projects

Village Roadshow Theme Parks
Village Roadshow Video Busters
Automated Game Mastering

Publications

• Jessica Rivera Villicana, Fabio Zambetta, James Harland and Marsha Berry. Using BDI to Model Players Behaviour in an Interactive Fiction Game. In: Proceedings of the Ninth International Conference on Interactive Digital Storytelling (ICIDS 2015), Los Angeles California, November 15-18 (2016).
• Marco Tamassia, William Raffe, Rafet Sifa, Anders Drachen, Fabio Zambetta and Michael Hitchens. Predicting Player Churn in Destiny: A Hidden Markov Models Approach to Predicting Player Departure in a Major Online Game. In: Proceedings of the Computational Intelligence and Games (IEEE CIG 2016), Santorini, Greece, 20-23 September (2016).
• Geoffrey W Lee, Fabio Zambetta, Xiaodong Li and Antonio G Paolini. Utilising reinforcement learning to develop strategies for driving auditory neural implants. Journal of Neural Engineering, Volume 13, Number 4 (2016).
• Marco Tamassia, Fabio Zambetta, William L. Raffe, Florian ‘Floyd’ Mueller, Xiaodong Li:
  Dynamic Choice of State Abstraction in Q-Learning. ECAI 2016: 46-54 (2016).
• Jessica Rivera-Villicana, Fabio Zambetta, James Harland, Marsha Berry:
  Towards a BDI Player Model for Interactive Narratives. ECAI 2016: 1648-1649.
• Edward Booth, John Thangarajah, Fabio Zambetta. Applying norms and preferences for designing flexible game rules. IJAOSE 5(1): 69-103 (2015).
• Raffe, W.,Zambetta, F.,Li, X.,Kenneth, S. Integrated approach to personalized procedural map generation using evolutionary algorithms In: IEEE Transactions on Computational Intelligence and AI in Games, 7, 139 – 155 (2015)
• Tamassia, M.,Zambetta, F.,Raffe, W.,Li, X. Learning options for an MDP from demonstrations In: Artificial Life and Computational Intelligence, Newcastle, Australia, 5-7 February (2015).
• Raffe, W.,Tamassia, M.,Zambetta, F.,Li, X.,Pell, S.,Mueller, F. (2015). Player-computer interaction features for designing digital play experiences across six degrees of water contactIn: Proceedings of the 015 Annual Symposium on Computer-Human Interaction in Play (CHI PLAY 2015), London, United Kingdom, 5-7 October (2015).
• Ivanovic, J.,Raffe, W.,Zambetta, F.,Li, X. (2015). Combining Monte Carlo tree search and apprenticeship learning for capture the flag In: Proceedings of the Computational Intelligence and Games (IEEE CIG 2015), Tainan, Taiwan, 31 August – 2 September (2015).
• Dann, M.,Zambetta, F.,Thangarajah, J. (2015). An improved approach to reinforcement learning in computer go In: Proceedings of the Computational Intelligence and Games (IEEE CIG 2015), Tainan, Taiwan, 31 August – 2 September (2015).
• Booth, E.,Thangarajah, J.,Zambetta, F. (2015). Flexible story generation with Norms and Preferences in computer role playing games In: Proceedings of the Computational Intelligence and Games (IEEE CIG 2015), Tainan, Taiwan, 31 August – 2 September (2015).
• Raffe, W.,Tamassia, M.,Zambetta, F.,Li, X.,Mueller, F. (2015). Enhancing theme park experiences through adaptive cyber-physical play In: Proceedings of the Computational Intelligence and Games (IEEE CIG 2015), Tainan, Taiwan, 31 August – 2 September (2015).
• Karpinskyj, S.,Zambetta, F.,Cavedon, L. Video game personalisation techniques: A comprehensive survey In: Entertainment Computing, 5, 211 – 218 (2014)
• Lee, G.,Luo, M.,Zambetta, F.,Li, X. (2014). Learning a super mario controller from examples of human play In: Proceedings of the 2014 IEEE Congress on Evolutionary Computation (CEC2014), Beijing, China, 6 – 11 July (2014).
• Ivanovic, J.,Zambetta, F.,Li, X.,Rivera Villicana, J. (2014). Reinforcement learning to control a commander for capture the flag In: Proceedings of the 2014 IEEE Conference on Computational Intelligence and Games (CIG), Dortmund, Germany, 26 – 29 August (2014).