The AI and Games Co-Revolution - Georgios Yannakakis
- 1. @yannakakis The AI and Games Co-Revolution © ennigmatic
- 4. Making computers able to do things which currently only humans can do
- 5. Making computers able to do things which currently only humans can do in games
- 6. What do humans do in games?
- 7. Play
- 8. Is the AI playing to win? Is the AI taking the role of a human player?
- 12. Trivedi, Liapis and Yannakakis, Contrastive Learning of Generalized Game Representations, IEEE Conference on Games, 2021
- 13. Trivedi, Liapis and Yannakakis, Contrastive Learning of Generalized Game Representations, IEEE Conference on Games, 2021
- 14. Design
- 16. Georgios N. Yannakakis, Antonios Liapis and Constantine Alexopoulos: "Mixed-Initiative Co-Creativity," in Proc. of the ACM Conference on Foundations of Digital Games, 2014.
- 17. Gravina, Liapis and Yannakakis: "Constrained Surprise Search for Content Generation," in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG). 2016.
- 18. Karavolos, Liapis, and Yannakakis: “A Multi-Faceted Surrogate Model for Search-based Procedural Content Generation," IEEE Transactions on Games, 2019
- 19. Experience
- 20. G. N. Yannakakis, P. Spronck, D. Loiacono and E. Andre, “Player Modeling,” in Togelius et al., (Eds.) Dagstuhl Seminar on Artificial and Computational Intelligence in Games, 2013. AI/ML/Stats Neutral
- 21. Arousal X Y Happier Valence Arousal Yannakakis, Cowie, Busso, The Ordinal Nature of Emotions: An Emerging Approach, IEEE Transactions on Affective Computing, 2018
- 22. The video says it all https://drive.google.com/file/d/1XfbFzdcfFiCKp3KG FHSB854mpn40mPgO/view Melhart, D., Azadvar, A., Canossa, A., Liapis, A., & Yannakakis, G. N. (2019). Your Gameplay Says it All: Modelling Motivation in Tom Clancy's The Division. Proceedings of the IEEE Conference on Games, 2019
- 23. Makantasis, Liapis and Yannakakis The Pixels and Sounds of Emotion: General-Purpose Representations of Arousal in Games, IEEE Trans. On Affective Computing, 2021
- 24. Gravina, Melhart, Yannakakis Moment-to-moment Engagement Prediction through the Eyes of the Observer: PUBG Streaming on Twitch, In Proc. of FDG, 2020
- 25. AGAIN Dataset Affect Game AnnotatIoN arXiv:2104.02643 Currently • 124 participants • 1,100+ gameplays • 37+ hours of annotated videos tamed-project.eu
- 26. General Models Player Arousal Modelling arXiv:2104.02643 100% 80% 50% 65% TinyCars ApexSpeed Solid TopDown Heist! Endless Shootout Run’N’Gun Pirates! Game-Based Models (trained on 1 game) Genre-Based Models (trained on 2 games) General Models (trained on 8 games) Melhart, Liapis and Yannakakis Towards General Models of Player Experience: A Study Within Genres, IEEE Conference on Games, 2021
- 27. Beyond Games?
- 28. Liapis, Martínez, Togelius, and Yannakakis: "Transforming Exploratory Creativity with DeLeNoX," in Proceedings of the Fourth International Conference on Computational Creativity, 2013.
- 29. Liu, Snodgrass, Khalifa, Risi, Yannakakis, Togelius, “Deep learning for procedural content generation” Neural Computing and Applications, 2020
- 30. Xylakis, Liapis and Yannakakis, Architectural Form and Affect: A Spatiotemporal Study of Arousal (under review) 2021
- 31. Gravina, Khalifa, Liapis, Togelius, Yannakakis, “Procedural content generation through quality diversity”, IEEE Conference on Games, 2019
- 32. Galanos, Liapis, Yannakakis, ARCH- Elites: Quality-Diversity for Urban Design, GECCO, 2021
- 33. A calm abstract painting A happy genre painting A happy sketch n study An angry landscape An angry portrait A depressed cityscape A depressed abstract painting A calm still life Semantic-driven affect-based painting generation
- 35. Obstacle tower game Deepmind’s stuff THE CO-REVOLUTION SLIDE S Risi, J Togelius. Increasing generality in machine learning through procedural content generation, Nature Machine Intelligence, 2020 Camilleri et al, Platformer Level Design for Player Believability, IEEE CIG, 2016 Wang et al. Paired open-ended trailblazer (POET): Endlessly generating increasingly complex and diverse learning environments and their solutions, 2019.
- 36. Shu, Liu and Yannakakis, Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Study, IEEE Conference on Games, 2021
- 37. Games... …the final frontier for AI
- 38. AI... …the final frontier for Games
- 39. Thank you! gameaibook.org and school.gameaibook.org