Projects

Sentient Designs

Sentient Designs is a collection of computer-aided design tools, which serve as both a stepping stone and an experiment in placing the computer in the role of a human's equal. Sentient Designs envision an artificial designer able to contribute to the creativity of its human colleague via the suggestion of novel alternatives which are tailored to the aesthetics, end-goals and design processes of the user.

Sentient Sketchbook

Sentient Sketchbook is a tool which supports the design of map sketches via an intuitive interface, via real-time feedback regarding the map's playability or balance, and via the suggestion of alternative map designs. The tool assists the level designer as it automatically tests maps for playability constraints, calculates and displays navigable paths, evaluates the map on gameplay properties and adds details to the coarse map sketch. Additionally, the tool aims to inspire the designer through the suggestion of map alternatives generated via genetic search.

Relevant Publications

  • Antonios Liapis, Georgios N. Yannakakis, Julian Togelius: "Sentient Sketchbook: Computer-Aided Game Level Authoring," in Proceedings of the 8th Conference on the Foundations of Digital Games, 2013, pp. 213-220. PDF BibTex

  • Georgios N. Yannakakis, Antonios Liapis, Constantine Alexopoulos: "Mixed-Initiative Co-Creativity," in Proceedings of the 9th Conference on the Foundations of Digital Games, 2014. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis, Julian Togelius: "Towards a Generic Method of Evaluating Game Levels," in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 2013. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis: "Refining the Paradigm of Sketching in AI-Based Level Design," in Proceedings of the AAAI Artificial Intelligence for Interactive Digital Entertainment Conference, 2015. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis, Julian Togelius: "Designer Modeling for Sentient Sketchbook," in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG), 2014. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis, Julian Togelius: "Enhancements to Constrained Novelty Search: Two-Population Novelty Search for Generating Game Content," in Proceedings of the Genetic and Evolutionary Competition Conference, 2013, pp. 343-350. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis, Julian Togelius: "Generating Map Sketches for Strategy Games," in Proceedings of Applications of Evolutionary Computation, vol. 7835, LNCS. Springer, 2013, pp. 264-273. PDF BibTex

  • Mike Preuss, Antonios Liapis, Julian Togelius: "Searching for Good and Diverse Game Levels," in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG), 2014. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis, Constantine Alexopoulos and Phil Lopes: "Can Computers Foster Human Users' Creativity? Theory and Praxis of Mixed-Initiative Co-Creativity," Digital Culture & Education (DCE), 8 (2). 2016. PDF BibTex

  • Antonios Liapis and Georgios N. Yannakakis: "Boosting Computational Creativity with Human Interaction in Mixed-Initiative Co-Creation Tasks," in Proceedings of the ICCC workshop on Computational Creativity and Games. 2016. PDF BibTex

  • Antonios Liapis: "Map Sketch Generation as a Service," in Proceedings of the AIIDE workshop on Experimental AI in Games, 2015. PDF BibTex

Sentient World

Sentient World is a tool which allows a designer to progressively add details to a rough sketch through the process of iterative refining. Iterative refining is accomplished by artificial neural networks (ANNs) trained via gradient search to conform to low-resolution sketches submitted by the designer; the infinite resolution potential of ANNs is then used to create higher-resolution maps which are submitted back to the designer to accept, reject, or edit.

Relevant Publications

  • Antonios Liapis, Georgios N. Yannakakis, Julian Togelius: "Sentient World: Human-Based Procedural Cartography," in Proceedings of Evolutionary and Biologically Inspired Music, Sound, Art and Design (EvoMusArt), vol. 7834, LNCS. Springer, 2013, pp. 180-191. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis, Constantine Alexopoulos and Phil Lopes: "Can Computers Foster Human Users' Creativity? Theory and Praxis of Mixed-Initiative Co-Creativity," Digital Culture & Education (DCE), 8 (2). 2016. PDF BibTex

  • Antonios Liapis and Georgios N. Yannakakis: "Boosting Computational Creativity with Human Interaction in Mixed-Initiative Co-Creation Tasks," in Proceedings of the ICCC workshop on Computational Creativity and Games. 2016. PDF BibTex

Automated Spaceship Design

The Spaceship Design tool is an experiment in interactive evolution where the user's visual taste is captured via adaptive computational models. Identifying and measuring seven visual properties inspired by cognitive psychology as well as neuroscience, constrained neuroevolution of augmenting topologies is used to automatically generate spaceships which epitomize one or more of these visual properties. Moreover, by devising a measure of aesthetic quality which can adjust the importance of these visual properties according to a user's selection among presented content, the system is able both to identify the visual taste of the user and to accommodate it by generating spaceships which epitomize the aesthetic properties most prominent in the user-selected content.

Relevant Publications

  • Antonios Liapis, Georgios N. Yannakakis, Julian Togelius: "Adapting Models of Visual Aesthetics for Personalized Content Creation," IEEE Transactions on Computational Intelligence and AI in Games 4(3), 2012, pp. 213-228. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis, Julian Togelius: "Optimizing Visual Properties of Game Content through Neuroevolution," in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 2011. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis, Julian Togelius: "Neuroevolutionary Constrained Optimization for Content Creation," in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG), 2011, pp. 71-78. PDF BibTex

  • Antonios Liapis, Hector P. Martinez, Julian Togelius, Georgios N. Yannakakis: "Transforming Exploratory Creativity with DeLeNoX," in Proceedings of the Fourth International Conference on Computational Creativity, 2013, pp. 56-63. PDF BibTex

  • Antonios Liapis and Georgios N. Yannakakis: "Boosting Computational Creativity with Human Interaction in Mixed-Initiative Co-Creation Tasks," in Proceedings of the ICCC workshop on Computational Creativity and Games. 2016. PDF BibTex

MiniDungeons

MiniDungeons is a simple turn-based roguelike puzzle game, implemented as a benchmark problem for modeling decision-making styles of human players. In every MiniDungeon level, the hero (controlled by the player) starts at the level's entrance and must navigate to the level exit while collecting treasures, killing monsters and drinking healing potions. The MiniDungeons game was created for two purposes: (a) to investigate how human players enact decision making styles in a simple game, and (b) to construct artificial agents able to represent such decision making styles. These artificial agents are identified as procedural personas and make decisions based on a utility (e.g. kill monsters, collect treasure, survive or speed run to the exit) specified by the human designer. The playtraces of such procedural personas can act as proxies of human playtraces during the design of game levels or new game rules. Moreover, the procedural personas can act as critics of an automated or mixed-initiative generator of new content (levels, rules) for MiniDungeons.

Relevant Publications

  • Christoffer Holmgard, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis: "Evolving Personas for Player Decision Modeling," in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG), 2014. PDF BibTex

  • Antonios Liapis, Christoffer Holmgard, Georgios N. Yannakakis, Julian Togelius: "Procedural Personas as Critics for Dungeon Generation," in Applications of Evolutionary Computation, vol. 9028, LNCS. Springer, 2015. PDF BibTex

  • Christoffer Holmgard, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis: "Generative Agents for Player Decision Modeling in Games," in Poster Proceedings of the 9th Conference on the Foundations of Digital Games, 2014. PDF BibTex

  • Christoffer Holmgard, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis: "Personas versus Clones for Player Decision Modeling," in Proceedings of the International Conference on Entertainment Computing (ICEC), 2014. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis: "Refining the Paradigm of Sketching in AI-Based Level Design," in Proceedings of the AAAI Artificial Intelligence for Interactive Digital Entertainment Conference, 2015. PDF BibTex

MiniDungeons 2

MiniDungeons 2 is a turn-based roguelike puzzle game, intended to be played on mobile devices; it was designed to provide a complex yet fully observable and deterministic environment for modeling decision-making styles of human players. As in MiniDungeons, the hero (controlled by the player) starts at the level's entrance and must navigate to the level exit while collecting treasures, killing monsters and drinking healing potions. Unlike MiniDungeons however, there is a multitude of monsters that can move around the level, with different behaviors, priorities, and interaction rules. MiniDungeons 2 offers a complex and dynamic environment which challenges the design of efficient and expressive artificial agents, identified as procedural personas, that play the game using their own personal notion of utility (e.g. kill monsters, collect treasure, survive or speed run to the exit). The playtraces of such procedural personas can act as proxies of human playtraces during the design of new game levels or new game rules.

Relevant Publications

  • Christoffer Holmgard, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis: "Monte-Carlo Tree Search for Persona Based Player Modeling," in Proceedings of the AIIDE workshop on Player Modeling, 2015. PDF BibTex

Data Adventures

The goal of the data adventures project is to generate adventure games based on open data (for instance Wikipedia articles, Wikimedia commons and OpenStreetMaps). The games generated focus mainly on discovery of visual and verbal clues and pieces of NPC dialogue. Fundamentally, the player's goal is to find the location of a certain person, starting from the location of another person or clue. To do so, players can travel between different countries and cities, and explore buildings in each city. The scope of these generated games can be adjusted; an example domain currently investigated is the discovery of the culprit in a murder case.

Relevant Publications

  • Gabriella A. B. Barros, Antonios Liapis and Julian Togelius: "Murder Mystery Generation from Open Data," in Proceedings of the International Conference on Computational Creativity. 2016. PDF BibTex

  • Gabriella A. B. Barros, Antonios Liapis and Julian Togelius: "Playing with Data: Procedural Generation of Adventures from Open Data," in Proceedings of the International Joint Conference of DiGRA and FDG. 2016. PDF BibTex

  • Gabriella A. B. Barros, Antonios Liapis, Julian Togelius: "Data Adventures," in Proceedings of the FDG workshop on Procedural Content Generation in Games, 2015. PDF BibTex

Sonancia

Sonancia is a system built for generating multiple facets of horror games, with the intention of creating tense and frightful experiences. Sonancia generates the architecture of a haunted mansion (with rooms and doors which may contain monsters or quest items) as well as the level's soundscape by allocating audio assets within the rooms and mixing them as the player traverses the level. Level generation and soundscape generation are orchestrated by notions of tension and suspense; the level generator attempts to match a designer-specified progression of tension while the sound generator attempts to prompt the player's suspense in rooms where tension is low.

Relevant Publications

  • Phil Lopes, Antonios Liapis, Georgios N Yannakakis: "Targeting Horror via Level and Soundscape Generation," in Proceedings of the AAAI Artificial Intelligence for Interactive Digital Entertainment Conference, 2015. PDF BibTex

  • Phil Lopes, Antonios Liapis and Georgios N. Yannakakis: "Framing Tension for Game Generation," in Proceedings of the International Conference on Computational Creativity. 2016. PDF BibTex

  • Phil Lopes, Antonios Liapis, Georgios N Yannakakis: "Sonancia: Sonification of Procedurally Generated Game Levels," in Proceedings of the ICCC workshop on Computational Creativity & Games, 2015. PDF BibTex

  • Phil Lopes, Antonios Liapis and Georgios N. Yannakakis: "Modelling Affect for Horror Soundscapes," IEEE Transactions of Affective Computing, 2017. PDF BibTex

  • Phil Lopes, Georgios N. Yannakakis and Antonios Liapis. 2017. "RankTrace: Relative and Unbounded Affect Annotation," In Proceedings of the International Conference on Affective Computing and Intelligent Interaction, 2017. PDF BibTex

  • Elizabeth Camilleri, Georgios N. Yannakakis and Antonios Liapis. 2017. "Towards General Models of Player Affect," In Proceedings of the International Conference on Affective Computing and Intelligent Interaction, 2017. PDF BibTex

Iconoscope

Iconoscope is a multi-player digital game intended to infuse creativity to the learning process, either as a trigger at the beginning of a learning unit or as part of a toolbox used to explore a given theme. Iconoscope is played on Android tablets by 4 or more players in the vicinity of each other: the goal is for each player to create an icon depicting a concept which confuses the other players. All players choose one among three concepts which are abstract themselves (e.g. "tolerance", "acceptance" and "solidarity") and attempt to depict it using simple shapes and colors. Once all players are finished, players vote for other players' icons by attempting to guess which of the three concepts is depicted. The most ambiguous icon (collecting as many incorrect as correct guesses) is the winner.

Relevant Publications

  • Antonios Liapis: "Mixed-initiative Creative Drawing with webIconoscope," In Proceedings of the 6th International Conference on Computational Intelligence in Music, Sound, Art and Design (EvoMusArt), vol. 10198, LNCS. Springer, 2017. PDF BibTex

  • Antonios Liapis, Amy K. Hoover, Georgios N. Yannakakis, Constantine Alexopoulos, Evangelia V. Dimaraki: "Motivating Visual Interpretations in Iconoscope: Designing a Game for Fostering Creativity," in Proceedings of the 10th Conference on the Foundations of Digital Games, 2015. PDF BibTex

  • Antonios Liapis, Georgios N. Yannakakis, Constantine Alexopoulos and Phil Lopes: "Can Computers Foster Human Users' Creativity? Theory and Praxis of Mixed-Initiative Co-Creativity," Digital Culture & Education (DCE), 8 (2). 2016. PDF BibTex

  • Antonios Liapis and Georgios N. Yannakakis: "Boosting Computational Creativity with Human Interaction in Mixed-Initiative Co-Creation Tasks," in Proceedings of the ICCC workshop on Computational Creativity and Games. 2016. PDF BibTex

Coralize

Coralize is a plugin for the Unity 3D game engine, and encompasses a library of generators for marine organisms, i.e. stony corals, soft corals and sponges. The parameterizable generators allow a user to adjust the parameters in order to create visually appealing 3D meshes. Such meshes can be placed directly in a Unity scene by a scene designer or automatically populate a seabed or reef.

Relevant Publications

  • Ryan Abela, Antonios Liapis, Georgios N. Yannakakis: "A Constructive Approach for the Generation of Underwater Environments," in Proceedings of the FDG workshop on Procedural Content Generation in Games, 2015. PDF BibTex

Multi-floor FPS Level Generation

First person shooter levels in the Cube 2 engine are generated via a search-based generative process. Genetic algorithms evolve the level's architecture and the placement of powerups and player spawnpoints, generating levels with one floor or two floors. The evaluation of generated levels combines metrics collected from simulations of artificial agents competing in the level and theory-based heuristics targeting general level design patterns.

Relevant Publications

  • William Cachia, Antonios Liapis, Georgios N. Yannakakis: "Multi-Level Evolution of Shooter Levels," in Proceedings of the AAAI Artificial Intelligence for Interactive Digital Entertainment Conference, 2015. PDF BibTex