Christian Guckelsberger

PhD Student

EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence (IGGI)

About me

I’m a PhD student in the Computational Creativity Group. I’m also a member of IGGI, the EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence.

I am interested in how we can create artificial systems that would be deemed creative in their own right by unbiased observers. I address this challenge with formal models of intrinsic motivation. I show both theoretically and in applied studies that models of intrinsic motivation can give rise to more general, robust and adaptive creative systems. Video games make an ideal application domain for this work, as they represent arbitrarily complex abstractions of the real world, and a challenging, multi-faceted domain for designers.

I have a Magister Artium in Computer Science, History of Art and Business Studies and a BSc in Computer Science. For my theses, I worked on intrinsic motivation in multi-agent systems, and on algorithms for the serendipitous recommendation of art. During my studies, I gained industrial experience at the research department of SAP SE and worked as a research assistant at Technical University Darmstadt. I am an open minded, passionate researcher and draw on an interdisciplinary approach. My general interests are in Computational Creativity and AI, Machine Learning and Information Theory.

My core research focusses on three challenges. I employ formal models of intrinsic motivation to:

  • Realise intentional agency in General AI and Computational Creativity.
  • Create General Non-Player Characters which exhibit creative, companion-/enemy-like behaviour in an arbitrary video game.
  • Predict a player’s experience of video game content without involving a human player or designer.

My thesis is supervised by Simon Colton (Goldsmiths/Falmouth), Paul Cairns (York), Jeremy Gow (Goldsmiths) and Christoph Salge (NYU/Hertfordshire).

Together with Christoph Salge and Tobias Mahlmann, I co-presented the first tutorial on Intrinsic Motivation in General Game Playing and NPCs at the Computational Intelligence and Games conference (CIG’16, Link).

I also contributed to STATSREP-ML, an open-source tool for automating the process of evaluating machine-learning results. You can find the code and instructions here.

You can contact me on .[at].., or find me on Twitter @CreativeEndvs.

You can find my academic CV here.

Publications

Journal Articles

Schulz, Axel; Guckelsberger, Christian; Janssen, Frederik

Semantic Abstraction for Generalization of Tweet Classification: An Evaluation on Incident-Related Tweets (Journal Article)

In: Semantic Web, 2015.

(Abstract | Links | BibTeX)

Guckelsberger, Christian; Polani, Daniel

Effects of Anticipation in Individually Motivated Behaviour on Survival and Control in a Multi-Agent Scenario with Resource Constraints (Journal Article)

In: Entropy, 16 (6), pp. 3357–3378, 2014, ISSN: 1099-4300.

(Abstract | Links | BibTeX)

Inproceedings

Guckelsberger, Christian; Salge, Christoph; Gow, Jeremy; Cairns, Paul

Predicting Player Experience Without the Player. An Exploratory Study (Inproceedings)

In: Proc. ACM Symp. on Computer-Human Interaction in Play (CHIPlay’17), 2017.

(Abstract | Links | BibTeX)

Guckelsberger, Christian; Salge, Christoph; Colton, Simon

Addressing the "Why?" in Computational Creativity: A Non-Anthropocentric, Minimal Model of Intentional Creative Agency (Inproceedings)

In: Proc. 8th Int. Conf. Computational Creativity, 2017 , 2017.

(Abstract | Links | BibTeX)

Denisova, Alena; Guckelsberger, Christian; Zendle, David

Challenge in Digital Games: Towards Developing a Measurement Tool (Inproceedings)

In: Proc. 35st ACM Conf. Human Factors in Computing Systems (CHI), ACM 2017.

(Links | BibTeX)

Guckelsberger, Christian; Salge, Christoph; Colton, Simon

Intrinsically Motivated General Companion NPCs via Coupled Empowerment Maximisation (Inproceedings)

In: Proc. IEEE Conf. Computational Intelligence in Games (CIG’16), IEEE, 2016.

(Abstract | Links | BibTeX)

Guckelsberger, Christian; Salge, Christoph

Does Empowerment Maximisation Allow for Enactive Artificial Agents? (Inproceedings)

In: Proc. 15th Int. Conf. Synthesis and Simulation of Living Systems (ALIFE), 2016.

(Abstract | Links | BibTeX)

Guckelsberger, Christian; Salge, Christoph; Saunders, Rob; Colton, Simon

Supportive and Antagonistic Behaviour in Distributed Computational Creativity via Coupled Empowerment Maximisation (Inproceedings)

In: Proc. 7th Int. Conf. Computational Creativity, 2016.

(Abstract | Links | BibTeX)

Llano, Maria Teresa; Guckelsberger, Christian; Hepworth, Rose; Gow, Jeremy; Corneli, Joseph; Colton, Simon

What If A Fish Got Drunk? Exploring the Plausibility of Machine-Generated Fictions (Inproceedings)

In: Proc. 7th Int. Conf. Computational Creativity, 2016.

(Abstract | Links | BibTeX)

Schulz, Axel; Guckelsberger, Christian; Schmidt, Benedikt

More Features Are Not Always Better: Evaluating Generalizing Models in Incident Type Classification of Tweets (Inproceedings)

In: Proc. Conf. Empirical Methods in Natural Language Processing (EMNLP), 2015.

(Abstract | Links | BibTeX)

Corneli, Joseph; Jordanous, Anna; Shepperd, Rosie; Llano, Maria Teresa; Misztal, Joanna; Colton, Simon; Guckelsberger, Christian

Computational Poetry Workshop: Making Sense of Work in Progress (Inproceedings)

In: Proc. 6th Int. Conf. Computational Creativity, 2015.

(Abstract | Links | BibTeX)

Llano, Maria Teresa; Cook, Michael; Guckelsberger, Christian; Colton, Simon; Hepworth, Rose

Towards the Automatic Generation of Fictional Ideas for Games (Inproceedings)

In: Experimental AI in Games (EXAG’14), a workshop collocated with the tenth annual AAAI conference on artificial intelligence and interactive digital entertainment (AIIDE’14). AAAI Publications, 2014.

(Abstract | Links | BibTeX)

Miscellaneous

Corneli, Joe; Guckelsberger, Christian; Jordanous, Anna; Pease, Alison; Colton, Simon; Erden, Yasemin J

Conference Report: AISB Members Workshop VII – Serendipity Symposium (Miscellaneous)

AISB Quarterly (147), 2017.

(Links | BibTeX)

Guckelsberger, Christian

Conference Report: Eighth International Conference on Computational Creativity (Miscellaneous)

AISB Quarterly (147), 2017.

(Links | BibTeX)

Guckelsberger, Christian; Probst, Florian; Schulz, Axel

Patent: Recommender System Employing Subjective Properties (pending) (Miscellaneous)

US 20160132954 A1, 2016.

(Abstract | Links | BibTeX)

Grebner, Olaf; Bruchmann, Max; Guckelsberger, Christian; Probst, Florian; Schulz, Axel

Patent: Reporting and Managing Incidents (Miscellaneous)

US 8786433 B2, 2014.

(Abstract | Links | BibTeX)

Technical Reports

Guckelsberger, Christian; Schulz, Axel

STATSREP-ML: Statistical evaluation & reporting framework for machine learning results (Technical Report)

Telecooperation Group, Technical University Darmstadt 2014.

(Abstract | Links | BibTeX)

Invited Talks

I have been invited to give the following tasks. Please click on the accordion tab for details.

University of Sussex Centre for Cognitive Science Seminar Series (COGS, 2017)

As part of the Centre for Cognitive Science (COGS) seminar series

Title:
Computational Creativity at the Edge of Being: Reconsidering Creativity and Intentional Agency in the Enactive AI Framework.

Abstract:
If we believe recent claims about Go-playing software and neural network painters, AI is about to cross one of the last frontiers to natural intelligence by becoming creative in their own right. In this work-in-progress talk, I argue that we are still far away from that, because artificial systems cannot account for their creative behaviour, without ultimately referring back to the values and goals of their designers. I propose an alternative research agenda to mainstream, anthropocentric computational creativity, in which this question of intentional creative agency is challenged from the bottom-up, based on autopoietic enactivism and minimally creative agents. The enactive artificial intelligence framework equips us with the necessary conditions for a system to ground value from its own perspective. I revisit different notions of creativity within the framework, and complement enactive AI’s theoretical requirements with candidate computational models to realise intentional creative agency. Our investigation suggests that we might never be able to replicate human creativity with intentional agency in artificial systems. However, it also highlights that the real value of computational creativity research might be found in going beyond the human domain.

ENactive Seminars Online (ENSO, 2017)

As part of the ENactive Seminars Online (ENSO) seminar series

Title:
Investigating the Role of Empowerment Maximisation in Constitutive Autonomy, Adaptivity and Open-Ended Development.

Abstract:
Constitutive autonomy has been proposed as the basis of intrinsic teleology, and is complemented by the concept of adaptivity to account for, amongst others, sense-making and intentional agency in biological and artificial systems. Empowerment maximisation, a formal, information-theoretic model of intrinsic motivation, has been proposed as a potentially universal model to realise critical aspects of constitutive autonomy and adaptivity in artificial systems. In this work-in-progress talk, I will re-evaluate our prior claims on the role of empowerment maximisation against a more comprehensive understanding of constitutive autonomy and adaptivity in minimal, autopoietic systems. I will discuss how empowerment goes beyond the present, formal requirements of adaptivity, and advocate its potential to facilitate open-ended development in artificial systems. The goal of this talk is to critically evaluate and deepen our arguments based on feedback from the community.

University of Hertfordshire (2017)

As part of the RAGS (Research in Adaptive systems Group Seminar) series

Title:
Predicting Player Experience Without the Player. An Exploratory Study Based on Empowerment as Intrinsic Motivation.

Abstract:
A key challenge of procedural content generation (PCG) in digital games is to evoke a certain player experience (PX), when we have no direct control over the content which gives rise to that experience. In this talk, I will argue that neither the rigorous methods to assess PX in HCI, nor specialised methods in PCG can solve this challenge, because they rely on people in the loop. In a recent paper to be presented at CHI’Play 2017, we propose to address this shortcoming by means of computational models of intrinsic motivation and AI game-playing agents. We hypothesise that our approach could be used to automatically predict PX across games and content types without relying on a human player or designer. I will use the first half of this talk to outline our approach and to present results from an exploratory study in level generation based on empowerment as specific model of intrinsic motivation. Based on a thematic analysis, we find that empowerment can be used to create levels with qualitatively different PX. In the second half of the talk, I will present our first steps towards a quantitative study and thus a full proof-of-concept. I will relate empowerment to established theories of PX in HCI and game design, and discuss potential applications beyond PCG.

New York University (2017)

Invited talk at NYU’s Game Innovation Lab

Title:
Intrinsic Motivation in Digital Games: From Steering Character Behaviour to Evaluating Game Content

Abstract:

Being intrinsically motivated means engaging in an activity for its inherent satisfactions, rather than for some separable consequence. People may play an open world game because they enjoy exploration, not because they aim for a prize as in an e-sports competition. Formal models of intrinsic motivation allow us to endow artificial agents with drives such as curiosity or learning progress. In this talk, I describe how these kinds of models address major challenges in both academic games research and practical games development. I present two studies based on empowerment, one specific model of intrinsic motivation, quantifying an agent’s perceivable influence on the environment. I show how empowerment can be used to create flexible and adaptive general non-player characters, and to predict players’ experience of procedurally generated content without a person in the loop.
University of Falmouth (2017)

Invited talk at the Metamaker’s Institute

Title:
Intrinsic Motivation in Digital Games: From Steering Character Behaviour to Evaluating Game Content

Abstract:

Being intrinsically motivated means engaging in an activity for its inherent satisfactions, rather than for some separable consequence. People may play an open world game because they enjoy exploration, not because they aim for a prize as in an e-sports competition. Formal models of intrinsic motivation allow us to endow artificial agents with drives such as curiosity or learning progress. In this talk, I describe how these kinds of models address major challenges in both academic games research and practical games development. I present two studies based on empowerment, one specific model of intrinsic motivation, quantifying an agent’s perceivable influence on the environment. I show how empowerment can be used to create flexible and adaptive general non-player characters, and to predict players’ experience of procedurally generated content without a person in the loop.
University of Hertfordshire (2016)

As part of the RAGS (Research in Adaptive systems Group Seminar) series

Title:
Collaboration in Co-Creative Scenarios via Coupled Empowerment Maximization: A Case-Study in Video Games

Abstract:
Recently, embodied and situated agents have become increasingly popular in co-creative systems (where humans and artificial agents jointly work on creative tasks). Intrinsically-motivated agents are particularly successful here, because of their capacity to act flexibly and adapt in open-ended interactions without clearly specified goals. Unfortunately, existing implementations do not manage to establish and maintain collaboration as a core mechanic in such systems without constraining the flexibility of the agents by means of explicitly specified interaction rules. This talk introduces the information-theoretic principle of coupled empowerment maximization as a means to establish a frame for both collaborative and antagonistic behaviour within which agents can interact with maximum flexibility. We study this mechanism in a dungeon-crawler video game testbed, to drive the behavior of an NPC supporting the human player. We demonstrate our progress, future challenges, and argue that the principle could eventually allow for the emergence of truly creative behavior.

Tungsten Centre for Intelligent Data Analytics (2016)

Title:
Does Empowerment Allow for Fully Enactive Artificial Agents?

Abstract:
The enactive AI framework wants to overcome the sense making limitations of embodied AI by drawing on the biosystemic foundations of enactive cognitive science. While embodied AI tries to ground meaning in sensorimotor interaction, enactive AI adds further requirements by grounding sensorimotor interaction in autonomous agency. At the core of this shift is the requirement for a truly intrinsic value function. We suggest that empowerment, an information-theoretic quantity based on an agent’s embodiment, represents such a function. We highlight the role of empowerment maximization in satisfying the requirements of enactive AI, i.e. establishing constitutive autonomy and adaptivity, in detail. We then argue that empowerment, grounded in a precarious existence, allows an agent to enact a world based on the relevance of environmental features in respect to its own identity.

Videos

My talk on “Investigating the Role of Empowerment Maximisation in Constitutive Autonomy, Adaptivity and Open-Ended Development” as part of the ENactive Seminars Online (ENSO) seminar series.

My talk on “Addressing the “Why?” in Computational Creativity: A Non-Anthropocentric, Minimal Model of Intentional Creative Agency” at the 8th International Conference on Computational Creativity in Atlanta, Georgia, June 19 – June 23, 2017 (paper link).

 

The video below showcases some of our research on intrinsically motivated, general companion NPCs (paper link).