User Modeling

Procedural content generation research has often focused on tailoring the artifacts created to a specific player's playstyle, preferences or skill. Similarly, several of my research projects aim to discover the preferences and visual taste of a designer from interactions with interactive evolutionary systems, learning the underlying factors of users' choices in order to better accomodate them.

RankTrace: Relative and Unbounded Affect Annotation

Phil Lopes, Georgios N. Yannakakis and Antonios Liapis. 2017.

Abstract: How should annotation data be processed so that it can best characterize the ground truth of affect? This paper attempts to address this critical question by testing various methods of processing annotation data on their ability to capture phasic elements of skin conductance. Towards this goal the paper introduces a new affect annotation tool, RankTrace, that allows for the annotation of affect in a continuous yet unbounded fashion. RankTrace is tested on first-person annotations of tension elicited from a horror video game. The key findings of the paper suggest that the relative processing of traces via their mean gradient yields the best and most robust predictors of phasic manifestations of skin conductance.

In Proceedings of the International Conference on Affective Computing and Intelligent Interaction, 2017. BibTex

Towards General Models of Player Affect

Elizabeth Camilleri, Georgios N. Yannakakis and Antonios Liapis. 2017.

Abstract: While the primary focus of affective computing has been on constructing efficient and reliable models of affect, the vast majority of such models are limited to a specific task and domain. This paper, instead, investigates how computational models of affect can be general across dissimilar tasks; in particular, in modeling the experience of playing very different video games. We use three dissimilar games whose players annotated their arousal levels on video recordings of their own playthroughs. We construct models mapping ranks of arousal to skin conductance and gameplay logs via preference learning and we use a form of cross-game validation to test the generality of the obtained models on unseen games. Our initial results comparing between absolute and relative measures of the arousal annotation values indicate that we can obtain more general models of player affect if we process the model output in an ordinal fashion.

In Proceedings of the International Conference on Affective Computing and Intelligent Interaction, 2017. BibTex

Modelling Affect for Horror Soundscapes

Phil Lopes, Antonios Liapis and Georgios N. Yannakakis

Abstract: The feeling of horror within movies or games relies on the audience’s perception of a tense atmosphere — often achieved through sound accompanied by the on-screen drama — guiding its emotional experience throughout the scene or game-play sequence. These progressions are often crafted through an a priori knowledge of how a scene or game-play sequence will playout, and the intended emotional patterns a game director wants to transmit. The appropriate design of sound becomes even more challenging once the scenery and the general context is autonomously generated by an algorithm. Towards realizing sound-based affective interaction in games this paper explores the creation of computational models capable of ranking short audio pieces based on crowdsourced annotations of tension, arousal and valence. Affect models are trained via preference learning on over a thousand annotations with the use of support vector machines, whose inputs are low-level features extracted from the audio assets of a comprehensive sound library. The models constructed in this work are able to predict the tension, arousal and valence elicited by sound, respectively, with an accuracy of approximately 65%, 66% and 72%.

IEEE Transactions of Affective Computing, 2017. BibTex

Discovering Social and Aesthetic Categories of Avatars: A Bottom-Up Artificial Intelligence Approach Using Image Clustering

Chong-U Lim, Antonios Liapis and D. Fox Harrell

Abstract: Videogame avatars are more than visual artifacts - they express cultural norms and expectations from both the real world and the fictional world. In this paper, we describe how artificial intelligence clustering can automatically discover distinct characteristics of players' avatars without prior knowledge of a system's underlying data structures. Using only avatar images collected from a study with 191 players, we applied two clustering techniques - namely non-negative matrix factorization and archetypal analysis - that automatically revealed and detected (1) an avatar's gender, (2) regions that appeared to isolate shapes of items and accessories, and (3) aesthetic preferences for particular colors (e.g., bright or muted) and shapes for different body parts. These clusters correlated with players' preferences for character abilities, e.g., male avatars in dark clothes correlated with having high physical but low magic-casting attributes. These findings show that a bottom-up analysis of images can reveal explicit categories like gender, but also implicit categories like preferences of players. We believe that such computational approaches can enable developers to (1) better understand players' desires and needs, (2) quantitatively view how systems may be limited in supporting players, and (3) find actionable solutions for these limitations.

in Proceedings of the International Joint Conference of DiGRA and FDG. 2016. BibTex

Monte-Carlo Tree Search for Persona Based Player Modeling

Christoffer Holmgard, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis

Abstract: Is it possible to conduct player modeling without any players? In this paper we use Monte-Carlo Tree Search-controlled procedural personas to simulate a range of decision making styles in the puzzle game MiniDungeons 2. The purpose is to provide a method for synthetic play testing of game levels with synthetic players based on designer intuition and experience. Five personas are constructed, representing five different decision making styles archetypal for the game. The personas vary solely in the weights of decision-making utilities that describe their valuation of a set affordances in MiniDungeons 2. By configuring these weights using designer expert knowledge, and passing the configurations directly to the MCTS algorithm, we make the personas exhibit a number of distinct decision making and play styles.

in Proceedings of the AIIDE workshop on Player Modeling, 2015. BibTex

Evolving Models of Player Decision Making: Personas versus Clones

Christoffer Holmgard, Antonios Liapis, Julian Togelius Georgios N. Yannakakis

Abstract: The current paper investigates multiple approaches to modeling human decision making styles for procedural play-testing. Building on decision and persona theory we evolve game playing agents representing human decision making styles. Three kinds of agents are evolved from the same representation: procedural personas, evolved from game designer expert knowledge, clones, evolved from observations of human play and aimed at general behavioral replication, and specialized agents, also evolved from observation, but aimed at determining the maximal behavioral replication ability of the representation. These three methods are then compared on their ability to represent individual human decision makers. Comparisons are conducted using three different proposed metrics that address the problem of matching decisions at the action, tactical, and strategic levels. Results indicate that a small gallery of personas evolved from designer intuitions can capture human decision making styles equally well as clones evolved from human play-traces for the testbed game MiniDungeons.

Entertainment Computing. Elsevier Volume 16, 2016, pp. 95–104. BibTex

Personas versus Clones for Player Decision Modeling

Christoffer Holmgard, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis

Abstract: The current paper investigates how to model human play styles. Building on decision and persona theory we evolve game playing agents representing human decision making styles. Two methods are developed, applied, and compared: procedural personas, based on utilities designed with expert knowledge, and clones, trained to reproduce playtraces. Additionally, two metrics for comparing agent and human decision making styles are proposed and compared. Results indicate that personas evolved from designer intuitions can capture human decision making styles equally well as clones evolved from human playtraces.

in Proceedings of the International Conference on Entertainment Computing (ICEC), 2014. BibTex

Designer Modeling for Sentient Sketchbook

Antonios Liapis, Georgios N. Yannakakis, Julian Togelius

Abstract: This paper documents the challenges in creating a computer-aided level design tool which incorporates computer-generated suggestions which appeal to the human user. Several steps are suggested in order to make the suggestions more appropriate to a specific user's overall style, current focus, and end-goals. Designer style is modeled via choice-based interactive evolution which adapts the impact of different dimensions of quality based on the designer's choice of certain suggestions over others. Modeling process is carried out similarly to style, but adapting to the current focus of the designer's actions. Goals are modeled by estimating the visual patterns of the designer's final artifact and changing the parameters of the algorithm to enforce such patterns on generated suggestions.

in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG), 2014. BibTex

Evolving Personas for Player Decision Modeling

Christoffer Holmgard, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis

Abstract: This paper explores how evolved game playing agents can be used to represent a priori defined archetypical ways of playing a test-bed game, as procedural personas. The end goal of such procedural personas is substituting players when authoring game content manually, procedurally, or both (in a mixed-initiative setting). Building on previous work, we compare the performance of newly evolved agents to agents trained via Q-learning as well as a number of baseline agents. Comparisons are performed on the grounds of game playing ability, generalizability, and conformity among agents. Finally, all agents' decision making styles are matched to the decision making styles of human players in order to investigate whether the different methods can yield agents who mimic or differ from human decision making in similar ways. The experiments performed in this paper conclude that agents developed from a priori defined objectives can express human decision making styles and that they are more generalizable and versatile than Q-learning and hand-crafted agents.

in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG), 2014. BibTex

Generative Agents for Player Decision Modeling in Games

Christoffer Holmgard, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis

Abstract: This paper presents a method for modeling player decision making through the use of agents as AI-driven personas. The paper argues that artificial agents, as generative player models, have properties that allow them to be used as psychometrically valid, abstract simulations of a human player's internal decision making processes. Such agents can then be used to interpret human decision making, as personas and playtesting tools in the game design process, as baselines for adapting agents to mimic classes of human players, or as believable, human-like opponents. This argument is explored in a crowdsourced decision making experiment, in which the decisions of human players are recorded in a small-scale dungeon themed puzzle game. Human decisions are compared to the decisions of a number of a priori defined "archetypical" agent-personas, and the humans are characterized by their likeness to or divergence from these. Essentially, at each step the action of the human is compared to what actions a number of reinforcement-learned agents would have taken in the same situation, where each agent is trained using a different reward scheme. Finally, extensions are outlined for adapting the agents to represent sub-classes found in the human decision making traces.

in Poster Proceedings of the 9th Conference on the Foundations of Digital Games, 2014. BibTex

Designer Modeling for Personalized Game Content Creation Tools

Antonios Liapis, Georgios N. Yannakakis, Julian Togelius

Abstract: With the growing use of automated content creation and computer-aided design tools in game development, there is potential for enhancing the design process through personalized interactions between the software and the game developer. This paper proposes designer modeling for capturing the designer's preferences, goals and processes from their interaction with a computer-aided design tool, and suggests methods and domains within game development where such a model can be applied. We describe how designer modeling could be integrated with current work on automated and mixed-initiative content creation, and envision future directions which focus on personalizing the processes to a designer's particular wishes.

in Proceedings of the AIIDE Workshop on Artificial Intelligence & Game Aesthetics, 2013. BibTex

Adaptive Game Level Creation through Rank-based Interactive Evolution

Antonios Liapis, Hector P. Martinez, Julian Togelius, Georgios N. Yannakakis

Abstract: This paper introduces Rank-based Interactive Evolution (RIE) which is an alternative to interactive evolution driven by computational models of user preferences to generate personalized content. In RIE, the computational models are adapted to the preferences of users which, in turn, are used as fitness functions for the optimization of the generated content. The preference models are built via ranking-based preference learning, while the content is generated via evolutionary search. The proposed method is evaluated on the creation of strategy game maps, and its performance is tested using artificial agents. Results suggest that RIE is both faster and more robust than standard interactive evolution and outperforms other state-of-the-art interactive evolution approaches.

in Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG), 2013. BibTex

Limitations of Choice-Based Interactive Evolution for Game Level Design

Antonios Liapis, Georgios N. Yannakakis, Julian Togelius

Abstract: This paper presents a tool geared towards the collaboration of a human and an artificial designer for the creation of game content. The framework combines procedural content generation using stochastic search with user input in the form of an initial goal statement as well as preference of generated results. Feedback from industry experts in a pilot user experiment showcased the limitations of this approach and the protocol chosen for evaluating the authoring tool. The limitations are discussed with respect to the suitability of interactive evolution for creative design and the design of experimental protocols for evaluating authoring tools for games.

in Proceedings of the AIIDE Workshop on Human Computation in Digital Entertainment, 2012. BibTex

Adapting Models of Visual Aesthetics for Personalized Content Creation

Antonios Liapis, Georgios N. Yannakakis, Julian Togelius

Abstract: This paper introduces a search-based approach to personalized content generation with respect to visual aesthetics. The approach is based on a two-step adaptation procedure where (1) the evaluation function that characterizes the content is adjusted to match the visual aesthetics of users and (2) the content itself is optimized based on the personalized evaluation function. To test the efficacy of the approach we design fitness functions based on universal properties of visual perception, inspired by psychological and neurobiological research. Using these visual properties we generate aesthetically pleasing 2D game spaceships via neuroevolutionary constrained optimization and evaluate the impact of the designed visual properties on the generated spaceships. The offline generated spaceships are used as the initial population of an interactive evolution experiment in which players are asked to choose spaceships according to their visual taste: the impact of the various visual properties is adjusted based on player preferences and new content is generated online based on the updated computational model of visual aesthetics of the player. Results are presented which show the potential of the approach in generating content which is based on subjective criteria of visual aesthetics.

IEEE Transactions on Computational Intelligence and AI in Games 4(3), 2012, pp. 213-228. BibTex