Search Results

Documents authored by Togelius, Julian


Document
Artificial and Computational Intelligence in Games: Revolutions in Computational Game AI (Dagstuhl Seminar 19511)

Authors: Jialin Liu, Tom Schaul, Pieter Spronck, and Julian Togelius

Published in: Dagstuhl Reports, Volume 9, Issue 12 (2020)


Abstract
The 2016 success of Google DeepMind’s AlphaGo, which defeated the Go world champion, and its follow-up program AlphaZero, has sparked a renewed interest of the general public in computational game playing. Moreover, game AI researchers build upon these results to construct stronger game AI implementations. While there is high enthusiasm for the rapid advances to the state-of-the-art in game AI, most researchers realize that they do not suffice to solve many of the challenges in game AI which have been recognized for decades. The Dagstuhl Seminar 19511 "Artificial and Computational Intelligence in Games: Revolutions in Computational Game AI" seminar was aimed at getting a clear view on the unsolved problems in game AI, determining which problems remain outside the reach of the state-of-the-art, and coming up with novel approaches to game AI construction to deal with these unsolved problems. This report documents the program and its outcomes.

Cite as

Jialin Liu, Tom Schaul, Pieter Spronck, and Julian Togelius. Artificial and Computational Intelligence in Games: Revolutions in Computational Game AI (Dagstuhl Seminar 19511). In Dagstuhl Reports, Volume 9, Issue 12, pp. 67-114, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2020)


Copy BibTex To Clipboard

@Article{liu_et_al:DagRep.9.12.67,
  author =	{Liu, Jialin and Schaul, Tom and Spronck, Pieter and Togelius, Julian},
  title =	{{Artificial and Computational Intelligence in Games: Revolutions in Computational Game AI (Dagstuhl Seminar 19511)}},
  pages =	{67--114},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2020},
  volume =	{9},
  number =	{12},
  editor =	{Liu, Jialin and Schaul, Tom and Spronck, Pieter and Togelius, Julian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.9.12.67},
  URN =		{urn:nbn:de:0030-drops-120113},
  doi =		{10.4230/DagRep.9.12.67},
  annote =	{Keywords: artificial intelligence, computational intelligence, game theory, games, optimization}
}
Document
Artificial and Computational Intelligence in Games: Integration (Dagstuhl Seminar 15051)

Authors: Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, and Julian Togelius

Published in: Dagstuhl Reports, Volume 5, Issue 1 (2015)


Abstract
This report documents Dagstuhl Seminar 15051 "Artificial and Computational Intelligence in Games: Integration". The focus of the seminar was on the computational techniques used to create, enhance, and improve the experiences of humans interacting with and within virtual environments. Different researchers in this field have different goals, including developing and testing new AI methods, creating interesting and believable non-player characters, improving the game production pipeline, studying game design through computational means, and understanding players and patterns of interaction. In recent years it has become increasingly clear that many of the research goals in the field require a multidisciplinary approach, or at least a combination of techniques that, in the past, were considered separate research topics. The goal of the seminar was to explicitly take the first steps along this path of integration, and investigate which topics and techniques would benefit most from collaboration, how collaboration could be shaped, and which new research questions may potentially be answered.

Cite as

Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, and Julian Togelius. Artificial and Computational Intelligence in Games: Integration (Dagstuhl Seminar 15051). In Dagstuhl Reports, Volume 5, Issue 1, pp. 207-242, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2015)


Copy BibTex To Clipboard

@Article{lucas_et_al:DagRep.5.1.207,
  author =	{Lucas, Simon M. and Mateas, Michael and Preuss, Mike and Spronck, Pieter and Togelius, Julian},
  title =	{{Artificial and Computational Intelligence in Games: Integration (Dagstuhl Seminar 15051)}},
  pages =	{207--242},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2015},
  volume =	{5},
  number =	{1},
  editor =	{Lucas, Simon M. and Mateas, Michael and Preuss, Mike and Spronck, Pieter and Togelius, Julian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.5.1.207},
  URN =		{urn:nbn:de:0030-drops-50404},
  doi =		{10.4230/DagRep.5.1.207},
  annote =	{Keywords: Multi-agent systems, Dynamical systems, Entertainment modeling, Player satisfaction, Game design, Serious games, Game theory}
}
Document
Complete Volume
DFU, Volume 6, Artificial and Computational Intelligence in Games, Complete Volume

Authors: Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, and Julian Togelius

Published in: Dagstuhl Follow-Ups, Volume 6, Artificial and Computational Intelligence in Games (2013)


Abstract
DFU, Volume 6, Artificial and Computational Intelligence in Games, Complete Volume

Cite as

Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, and Julian Togelius. DFU, Volume 6, Artificial and Computational Intelligence in Games, Complete Volume. In Artificial and Computational Intelligence in Games. Dagstuhl Follow-Ups, Volume 6, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2013)


Copy BibTex To Clipboard

@Collection{DFU.Vol6.12191,
  title =	{{DFU, Volume 6, Artificial and Computational Intelligence in Games, Complete Volume}},
  booktitle =	{Artificial and Computational Intelligence in Games},
  series =	{Dagstuhl Follow-Ups},
  ISBN =	{978-3-939897-62-0},
  ISSN =	{1868-8977},
  year =	{2013},
  volume =	{6},
  editor =	{Lucas, Simon M. and Mateas, Michael and Preuss, Mike and Spronck, Pieter and Togelius, Julian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DFU.Vol6.12191},
  URN =		{urn:nbn:de:0030-drops-43518},
  doi =		{10.4230/DFU.Vol6.12191},
  annote =	{Keywords: Applications and Expert Systems: Games}
}
Document
Frontmatter

Authors: Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, and Julian Togelius

Published in: Dagstuhl Follow-Ups, Volume 6, Artificial and Computational Intelligence in Games (2013)


Abstract
Frontmatter, table of contents, preface, author list

Cite as

Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, and Julian Togelius. Frontmatter. In Artificial and Computational Intelligence in Games. Dagstuhl Follow-Ups, Volume 6, pp. 0:i-0:xiv, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2013)


Copy BibTex To Clipboard

@InCollection{lucas_et_al:DFU.Vol6.12191.i,
  author =	{Lucas, Simon M. and Mateas, Michael and Preuss, Mike and Spronck, Pieter and Togelius, Julian},
  title =	{{Frontmatter}},
  booktitle =	{Artificial and Computational Intelligence in Games},
  pages =	{0:i--0:xiv},
  series =	{Dagstuhl Follow-Ups},
  ISBN =	{978-3-939897-62-0},
  ISSN =	{1868-8977},
  year =	{2013},
  volume =	{6},
  editor =	{Lucas, Simon M. and Mateas, Michael and Preuss, Mike and Spronck, Pieter and Togelius, Julian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DFU.Vol6.12191.i},
  URN =		{urn:nbn:de:0030-drops-43315},
  doi =		{10.4230/DFU.Vol6.12191.i},
  annote =	{Keywords: Frontmatter, table of contents, preface, author list}
}
Document
Procedural Content Generation: Goals, Challenges and Actionable Steps

Authors: Julian Togelius, Alex J. Champandard, Pier Luca Lanzi, Michael Mateas, Ana Paiva, Mike Preuss, and Kenneth O. Stanley

Published in: Dagstuhl Follow-Ups, Volume 6, Artificial and Computational Intelligence in Games (2013)


Abstract
This chapter discusses the challenges and opportunities of procedural content generation (PCG) in games. It starts with defining three grand goals of PCG, namely multi-level multicontent PCG, PCG-based game design and generating complete games. The way these goals are defined, they are not feasible with current technology. Therefore we identify nine challenges for PCG research. Work towards meeting these challenges is likely to take us closer to realising the three grand goals. In order to help researchers get started, we also identify five actionable steps, which PCG researchers could get started working on immediately.

Cite as

Julian Togelius, Alex J. Champandard, Pier Luca Lanzi, Michael Mateas, Ana Paiva, Mike Preuss, and Kenneth O. Stanley. Procedural Content Generation: Goals, Challenges and Actionable Steps. In Artificial and Computational Intelligence in Games. Dagstuhl Follow-Ups, Volume 6, pp. 61-75, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2013)


Copy BibTex To Clipboard

@InCollection{togelius_et_al:DFU.Vol6.12191.61,
  author =	{Togelius, Julian and Champandard, Alex J. and Lanzi, Pier Luca and Mateas, Michael and Paiva, Ana and Preuss, Mike and Stanley, Kenneth O.},
  title =	{{Procedural Content Generation: Goals, Challenges and Actionable Steps}},
  booktitle =	{Artificial and Computational Intelligence in Games},
  pages =	{61--75},
  series =	{Dagstuhl Follow-Ups},
  ISBN =	{978-3-939897-62-0},
  ISSN =	{1868-8977},
  year =	{2013},
  volume =	{6},
  editor =	{Lucas, Simon M. and Mateas, Michael and Preuss, Mike and Spronck, Pieter and Togelius, Julian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DFU.Vol6.12191.61},
  URN =		{urn:nbn:de:0030-drops-43367},
  doi =		{10.4230/DFU.Vol6.12191.61},
  annote =	{Keywords: procedural content generation, video games}
}
Document
Towards a Video Game Description Language

Authors: Marc Ebner, John Levine, Simon M. Lucas, Tom Schaul, Tommy Thompson, and Julian Togelius

Published in: Dagstuhl Follow-Ups, Volume 6, Artificial and Computational Intelligence in Games (2013)


Abstract
This chapter is a direct follow-up to the chapter on General Video Game Playing (GVGP). As that group recognised the need to create a Video Game Description Language (VGDL), we formed a group to address that challenge and the results of that group is the current chapter. Unlike the VGDL envisioned in the previous chapter, the language envisioned here is not meant to be supplied to the game-playing agent for automatic reasoning; instead we argue that the agent should learn this from interaction with the system. The main purpose of the language proposed here is to be able to specify complete video games, so that they could be compiled with a special VGDL compiler. Implementing such a compiler could provide numerous opportunities; users could modify existing games very quickly, or have a library of existing implementations defined within the language (e.g. an Asteroids ship or a Mario avatar) that have pre-existing, parameterised behaviours that can be customised for the users specific purposes. Provided the language is fit for purpose, automatic game creation could be explored further through experimentation with machine learning algorithms, furthering research in game creation and design. In order for both of these perceived functions to be realised and to ensure it is suitable for a large user base we recognise that the language carries several key requirements. Not only must it be human-readable, but retain the capability to be both expressive and extensible whilst equally simple as it is general. In our preliminary discussions, we sought to define the key requirements and challenges in constructing a new VGDL that will become part of the GVGP process. From this we have proposed an initial design to the semantics of the language and the components required to define a given game. Furthermore, we applied this approach to represent classic games such as Space Invaders, Lunar Lander and Frogger in an attempt to identify potential problems that may come to light. Work is ongoing to realise the potential of the VGDL for the purposes of Procedural Content Generation, Automatic Game Design and Transfer Learning.

Cite as

Marc Ebner, John Levine, Simon M. Lucas, Tom Schaul, Tommy Thompson, and Julian Togelius. Towards a Video Game Description Language. In Artificial and Computational Intelligence in Games. Dagstuhl Follow-Ups, Volume 6, pp. 85-100, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2013)


Copy BibTex To Clipboard

@InCollection{ebner_et_al:DFU.Vol6.12191.85,
  author =	{Ebner, Marc and Levine, John and Lucas, Simon M. and Schaul, Tom and Thompson, Tommy and Togelius, Julian},
  title =	{{Towards a Video Game Description Language}},
  booktitle =	{Artificial and Computational Intelligence in Games},
  pages =	{85--100},
  series =	{Dagstuhl Follow-Ups},
  ISBN =	{978-3-939897-62-0},
  ISSN =	{1868-8977},
  year =	{2013},
  volume =	{6},
  editor =	{Lucas, Simon M. and Mateas, Michael and Preuss, Mike and Spronck, Pieter and Togelius, Julian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DFU.Vol6.12191.85},
  URN =		{urn:nbn:de:0030-drops-43385},
  doi =		{10.4230/DFU.Vol6.12191.85},
  annote =	{Keywords: Video games, description language, language construction}
}
Document
Artificial and Computational Intelligence in Games (Dagstuhl Seminar 12191)

Authors: Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, and Julian Togelius

Published in: Dagstuhl Reports, Volume 2, Issue 5 (2012)


Abstract
This report documents the program and the outcomes of Dagstuhl Seminar 12191 "Artificial and Computational Intelligence in Games". The aim for the seminar was to bring together creative experts in an intensive meeting with the common goals of gaining a deeper understanding of various aspects of artificial and computational intelligence in games, to help identify the main challenges in game AI research and the most promising venues to deal with them. This was accomplished mainly by means of workgroups on 14 different topics (ranging from search, learning, and modeling to architectures, narratives, and evaluation), and plenary discussions on the results of the workgroups. This report presents the conclusions that each of the workgroups reached. We also added short descriptions of the few talks that were unrelated to any of the workgroups.

Cite as

Simon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, and Julian Togelius. Artificial and Computational Intelligence in Games (Dagstuhl Seminar 12191). In Dagstuhl Reports, Volume 2, Issue 5, pp. 43-70, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2012)


Copy BibTex To Clipboard

@Article{lucas_et_al:DagRep.2.5.43,
  author =	{Lucas, Simon M. and Mateas, Michael and Preuss, Mike and Spronck, Pieter and Togelius, Julian},
  title =	{{Artificial and Computational Intelligence in Games (Dagstuhl Seminar 12191)}},
  pages =	{43--70},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2012},
  volume =	{2},
  number =	{5},
  editor =	{Lucas, Simon M. and Mateas, Michael and Preuss, Mike and Spronck, Pieter and Togelius, Julian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.2.5.43},
  URN =		{urn:nbn:de:0030-drops-36510},
  doi =		{10.4230/DagRep.2.5.43},
  annote =	{Keywords: Artificial Intelligence, Computational Intelligence, Computer Games}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail