Antonios Liapis
Antonios Liapis is a lecturer and researcher at the Institute of Digital Games, University of Malta. His research takes place on the crossroads of game design, artificial intelligence and computational creativity. Game design is usually human-driven design process and one of Dr Liapis's main research areas is exploring the limits of automated game design. [1]
Education[edit]
Liapis completed his PhD studies at the Center for Computer Games Research at the IT University of Copenhagen under supervision of Georgios Yannakakis. Before completing his PhD he received his M.Sc. degree in Information Technology through the Media Technology and Games program of IT University of Copenhagen and his 5-year Diploma in Electrical and Computer Engineering from the National Technical University of Athens.
Academic work[edit]
His PhD research revolved around mixed-initiative tools for the creation of game content as he believed these tools should both support a user in their design process but also contribute with novel ideas. He explores the generation of such ideas where a mixed-initiative tool should recognize the user's intentions, aesthetic preferences and design process and its suggestions should either be the next logical step towards the user's perceived goal or present an unexpected alternative which the designer hadn't thought of.
His research has been implemented as part of the Iconoscope game[2] where players are tasked to creatively interpret concepts (described linguistically) as icons (depicted visually) which convey the same message. An artificial intelligence agent uses the data gathered from the visual depictions submitted and proposes unexpected and meaningful suggestions meant to stimulate the creativity of the players.[3]
In order to make either type of suggestion meaningful, the computer must be able to capture the user's perceptual and cognitive mechanisms, and apply this knowledge to incite the creativity of the designer. Beyond mixed-initiative tools, his academic interests include fully-automated procedural content generation, digital aesthetics, computational creativity and evolutionary computation.
He has collaborated with Julian Togelius and Georgios Yannakakis including work on proposing two novelty search algorithms which search within both the feasible and the infeasible space. The proposed algorithms were applied to the problem of generating diverse but playable game levels, keeping in mind the larger problem of procedural game content generation. Their algorithm showed that the two-population constrained novelty search methods can create, under certain conditions, larger and more diverse sets of feasible game levels than current methods of novelty search, whether constrained or unconstrained. They also found that boosting the offspring in the genetic algorithm enhances performance in all cases of two-population novelty search.[4]
Publications[edit]
Liapis has published a number of papers on game design, artificial intelligence and computational creativity in addition to contributing book chapters to academic text books.
Book chapters[edit]
- Noor Shaker, Antonios Liapis, Julian Togelius, Ricardo Lopes, and Rafael Bidarra: "Constructive generation methods for dungeons and levels," In Procedural Content Generation in Games: A Textbook and an Overview of Current Research, Springer, 2016.[5]
- Antonios Liapis, Gillian Smith and Noor Shaker: "Mixed-initiative Content Creation," In Procedural Content Generation in Games: A Textbook and an Overview of Current Research, Springer, 2016.[5]
| Year | Paper | Award | Venue |
|---|---|---|---|
| 2015 | A. Liapis, C. Holmgard, G. N. Yannakakis, and J. Togelius, “Procedural Personas as Critics for Dungeon Generation” | Best Paper Award[6][not in citation given] | Applications of Evolutionary Computation |
| 2014 | A. Liapis, G. N. Yannakakis, and J. Togelius, ``Designer Modeling for Sentient Sketchbook” | Best Paper Award[7][not in citation given] | IEEE Conference on Computational Intelligence and Games |
| 2013 | A. Liapis, G. N. Yannakakis, J. Togelius: “Towards a Generic Method of Evaluating Game Levels” | Best Student Paper Award[8][not in citation given] | AAAI Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE) |
| 2013 | A. Liapis, G. N. Yannakakis, J. Togelius: “Enhancements to Constrained Novelty Search: Two-Population Novelty Search for Generating Game Content,” | Best Paper Award[9] | Genetic and Evolutionary Competition Conference (GECCO) |
Notable games[edit]
Liapis contributed to the design of the SIREN Game with Lead Designer Rilla Khaled and Georgios Yannakakis. SIREN Game was awarded European Learning Game of 2013 Award by the Games and Learning Alliance (GALA) Network of Excellence in 2013.
He also won a number of prizes as part of the IT University of Copenhagen In the Make Something Unreal Competition 2009 for modifications to The Witching Hour:
- Educational Category: 1st Place
- Best FPS Mod: Finalist
- Best Level for a Mod: Honorable Mention
References[edit]
- ↑ "AutoGame Design".
- ↑ "Iconoscope Home". iconoscope.institutedigitalgames.com. Retrieved 2018-02-02.
- ↑ Liapis, Antonios (2015). "Motivating Visual Interpretations in Iconoscope: Designing a Game for Fostering Creativity" (PDF). Proceedings of Foundations of Digital Games.
- ↑ Antonios Liapis, Georgios N. Yannakakis, Julian Togelius (2015). "Constrained Novelty Search: A Study on Game Content Generation" (PDF). Evolutionary Computation. 21(1): 101–129.CS1 maint: Multiple names: authors list (link)
- ↑ 5.0 5.1 "Procedural Content Generation in Games | A textbook and an overview of current research". pcgbook.com. Retrieved 2017-11-27.
- ↑ "Evostar 2015". www.evostar.org. Retrieved 2017-11-27.
- ↑ "proceedings [CIG 2014]". storage.kghost.de. Retrieved 2017-11-27.
- ↑ "Proceedings of the Ninth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-13)". www.aaai.org. Retrieved 2017-11-27.
- ↑ "GECCO 2013". www.sigevo.org. Retrieved 2017-11-27.
External links[edit]
This article "Antonios Liapis" is from Wikipedia. The list of its authors can be seen in its historical. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.
