Search Results for author: Julian Togelius

Found 130 papers, 40 papers with code

Making New Connections: LLMs as Puzzle Generators for The New York Times' Connections Word Game

no code implementations15 Jul 2024 Tim Merino, Sam Earle, Ryan Sudhakaran, Shyam Sudhakaran, Julian Togelius

Our findings show that LLMs are capable puzzle creators, and can generate diverse sets of enjoyable, challenging, and creative Connections puzzles as judged by human users.

Autoverse: An Evolvable Game Langugage for Learning Robust Embodied Agents

no code implementations5 Jul 2024 Sam Earle, Julian Togelius

We introduce Autoverse, an evolvable, domain-specific language for single-player 2D grid-based games, and demonstrate its use as a scalable training ground for Open-Ended Learning (OEL) algorithms.

Imitation Learning Reinforcement Learning (RL)

Goals as Reward-Producing Programs

no code implementations21 May 2024 Guy Davidson, Graham Todd, Julian Togelius, Todd M. Gureckis, Brenden M. Lake

People are remarkably capable of generating their own goals, beginning with child's play and continuing into adulthood.

Diversity Program Synthesis

Word2World: Generating Stories and Worlds through Large Language Models

1 code implementation6 May 2024 Muhammad U. Nasir, Steven James, Julian Togelius

Word2World leverages the abilities of LLMs to create diverse content and extract information.

Game Design

DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft

no code implementations23 Apr 2024 Sam Earle, Filippos Kokkinos, Yuhe Nie, Julian Togelius, Roberta Raileanu

In contrast, text-to-3D methods allow users to specify desired characteristics in natural language, offering a high amount of flexibility and expressivity.

Game Design text-guided-generation +1

Missed Connections: Lateral Thinking Puzzles for Large Language Models

no code implementations17 Apr 2024 Graham Todd, Tim Merino, Sam Earle, Julian Togelius

This is because the four categories ascend in complexity, with the most challenging category often requiring thinking about words in uncommon ways or as parts of larger phrases.

Sentence Sentence Embedding +1

The Ink Splotch Effect: A Case Study on ChatGPT as a Co-Creative Game Designer

no code implementations4 Mar 2024 Asad Anjum, Yuting Li, Noelle Law, M Charity, Julian Togelius

This paper studies how large language models (LLMs) can act as effective, high-level creative collaborators and ``muses'' for game design.

Chatbot Decision Making +1

Large Language Models and Games: A Survey and Roadmap

no code implementations28 Feb 2024 Roberto Gallotta, Graham Todd, Marvin Zammit, Sam Earle, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis

Recent years have seen an explosive increase in research on large language models (LLMs), and accompanying public engagement on the topic.

Alpha-wolves and Alpha-mammals: Exploring Dictionary Attacks on Iris Recognition Systems

no code implementations20 Nov 2023 Sudipta Banerjee, Anubhav Jain, Zehua Jiang, Nasir Memon, Julian Togelius, Arun Ross

A dictionary attack in a biometric system entails the use of a small number of strategically generated images or templates to successfully match with a large number of identities, thereby compromising security.

Iris Recognition

Evolutionary Machine Learning and Games

no code implementations20 Nov 2023 Julian Togelius, Ahmed Khalifa, Sam Earle, Michael Cerny Green, Lisa Soros

Evolutionary machine learning (EML) has been applied to games in multiple ways, and for multiple different purposes.

Fair GANs through model rebalancing for extremely imbalanced class distributions

no code implementations16 Aug 2023 Anubhav Jain, Nasir Memon, Julian Togelius

We do so by generating balanced data from an existing imbalanced deep generative model using an evolutionary algorithm and then using this data to train a balanced generative model.

Fairness Generative Adversarial Network

The Five-Dollar Model: Generating Game Maps and Sprites from Sentence Embeddings

1 code implementation8 Aug 2023 Timothy Merino, Roman Negri, Dipika Rajesh, M Charity, Julian Togelius

The five-dollar model is a lightweight text-to-image generative architecture that generates low dimensional images from an encoded text prompt.

Sentence Sentence Embeddings

Lode Enhancer: Level Co-creation Through Scaling

no code implementations3 Aug 2023 Debosmita Bhaumik, Julian Togelius, Georgios N. Yannakakis, Ahmed Khalifa

We explore AI-powered upscaling as a design assistance tool in the context of creating 2D game levels.

Lode Encoder: AI-constrained co-creativity

no code implementations2 Aug 2023 Debosmita Bhaumik, Ahmed Khalifa, Julian Togelius

We present Lode Encoder, a gamified mixed-initiative level creation system for the classic platform-puzzle game Lode Runner.

Generating Redstone Style Cities in Minecraft

no code implementations19 Jul 2023 Shuo Huang, Chengpeng Hu, Julian Togelius, Jialin Liu

Procedurally generating cities in Minecraft provides players more diverse scenarios and could help understand and improve the design of cities in other digital worlds and the real world.

Amorphous Fortress: Observing Emergent Behavior in Multi-Agent FSMs

no code implementations22 Jun 2023 M Charity, Dipika Rajesh, Sam Earle, Julian Togelius

We introduce a system called Amorphous Fortress -- an abstract, yet spatial, open-ended artificial life simulation.

Artificial Life

LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization

1 code implementation1 Jun 2023 Muhammad U. Nasir, Sam Earle, Christopher Cleghorn, Steven James, Julian Togelius

By merging the code-generating abilities of LLMs with the diversity and robustness of QD solutions, we introduce \texttt{LLMatic}, a Neural Architecture Search (NAS) algorithm.

Code Generation Diversity +2

Controllable Path of Destruction

no code implementations29 May 2023 Matthew Siper, Sam Earle, Zehua Jiang, Ahmed Khalifa, Julian Togelius

The PoD method is very data-efficient in terms of original training examples and well-suited to functional artifacts composed of categorical data, such as game levels and discrete 3D structures.

Practical PCG Through Large Language Models

no code implementations20 May 2023 Muhammad U Nasir, Julian Togelius

Large Language Models (LLMs) have proven to be useful tools in various domains outside of the field of their inception, which was natural language processing.

Zero-shot racially balanced dataset generation using an existing biased StyleGAN2

1 code implementation12 May 2023 Anubhav Jain, Nasir Memon, Julian Togelius

Facial recognition systems have made significant strides thanks to data-heavy deep learning models, but these models rely on large privacy-sensitive datasets.

Diversity Face Recognition

The Ethics of AI in Games

no code implementations12 May 2023 David Melhart, Julian Togelius, Benedikte Mikkelsen, Christoffer Holmgård, Georgios N. Yannakakis

Video games are one of the richest and most popular forms of human-computer interaction and, hence, their role is critical for our understanding of human behaviour and affect at a large scale.


Choose Your Weapon: Survival Strategies for Depressed AI Academics

no code implementations31 Mar 2023 Julian Togelius, Georgios N. Yannakakis

This is not an exhaustive list of strategies, and you may not agree with all of them, but it serves to start a discussion.

ChatGPT4PCG Competition: Character-like Level Generation for Science Birds

1 code implementation28 Mar 2023 Pittawat Taveekitworachai, Febri Abdullah, Mury F. Dewantoro, Ruck Thawonmas, Julian Togelius, Jochen Renz

An experiment is conducted to determine the effectiveness of several modified versions of this sample prompt on level stability and similarity by testing them on several characters.

Prompt Engineering

Level Generation Through Large Language Models

no code implementations11 Feb 2023 Graham Todd, Sam Earle, Muhammad Umair Nasir, Michael Cerny Green, Julian Togelius

Large Language Models (LLMs) are powerful tools, capable of leveraging their training on natural language to write stories, generate code, and answer questions.

Pathfinding Neural Cellular Automata

no code implementations17 Jan 2023 Sam Earle, Ozlem Yildiz, Julian Togelius, Chinmay Hegde

As a step toward developing such networks, we hand-code and learn models for Breadth-First Search (BFS), i. e. shortest path finding, using the unified architectural framework of Neural Cellular Automata, which are iterative neural networks with equal-size inputs and outputs.

A Dataless FaceSwap Detection Approach Using Synthetic Images

1 code implementation5 Dec 2022 Anubhav Jain, Nasir Memon, Julian Togelius

Face swapping technology used to create "Deepfakes" has advanced significantly over the past few years and now enables us to create realistic facial manipulations.

DeepFake Detection Face Swapping

Story Designer: Towards a Mixed-Initiative Tool to Create Narrative Structures

no code implementations11 Oct 2022 Alberto Alvarez, Jose Font, Julian Togelius

This paper presents Story Designer, a mixed-initiative co-creative narrative structure tool built on top of the Evolutionary Dungeon Designer (EDD) that uses tropes, narrative conventions found across many media types, to design these structures.

Diversity and Novelty MasterPrints: Generating Multiple DeepMasterPrints for Increased User Coverage

no code implementations11 Sep 2022 M Charity, Nasir Memon, Zehua Jiang, Abhi Sen, Julian Togelius

This work expands on previous advancements in genetic fingerprint spoofing via the DeepMasterPrints and introduces Diversity and Novelty MasterPrints.

Diversity Evolutionary Algorithms

Keke AI Competition: Solving puzzle levels in a dynamically changing mechanic space

no code implementations11 Sep 2022 M Charity, Julian Togelius

The Keke AI Competition introduces an artificial agent competition for the game Baba is You - a Sokoban-like puzzle game where players can create rules that influence the mechanics of the game.

Aesthetic Bot: Interactively Evolving Game Maps on Twitter

no code implementations9 Aug 2022 M Charity, Julian Togelius

This paper describes the implementation of the Aesthetic Bot, an automated Twitter account that posts images of small game maps that are either user-made or generated from an evolutionary system.

Learning Controllable 3D Level Generators

1 code implementation27 Jun 2022 Zehua Jiang, Sam Earle, Michael Cerny Green, Julian Togelius

Procedural Content Generation via Reinforcement Learning (PCGRL) foregoes the need for large human-authored data-sets and allows agents to train explicitly on functional constraints, using computable, user-defined measures of quality instead of target output.

Generating Diverse Indoor Furniture Arrangements

no code implementations20 Jun 2022 Ya-Chuan Hsu, Matthew C. Fontaine, Sam Earle, Maria Edwards, Julian Togelius, Stefanos Nikolaidis

To target specific diversity in the arrangements, we optimize the latent space of the GAN via a quality diversity algorithm to generate a diverse arrangement collection.

Diversity Generative Adversarial Network

Mutation Models: Learning to Generate Levels by Imitating Evolution

no code implementations11 Jun 2022 Ahmed Khalifa, Michael Cerny Green, Julian Togelius

Search-based procedural content generation (PCG) is a well-known method for level generation in games.

Watts: Infrastructure for Open-Ended Learning

1 code implementation28 Apr 2022 Aaron Dharna, Charlie Summers, Rohin Dasari, Julian Togelius, Amy K. Hoover

This paper proposes a framework called Watts for implementing, comparing, and recombining open-ended learning (OEL) algorithms.


Persona-driven Dominant/Submissive Map (PDSM) Generation for Tutorials

no code implementations11 Apr 2022 Michael Cerny Green, Ahmed Khalifa, M Charity, Julian Togelius

In this paper, we present a method for automated persona-driven video game tutorial level generation.


Transfer Dynamics in Emergent Evolutionary Curricula

no code implementations3 Mar 2022 Aaron Dharna, Amy K Hoover, Julian Togelius, L. B. Soros

Furthermore, we analyze the impact of the minimal criterion on generated level diversity and inter-species transfer.

Artificial Life Diversity

Path of Destruction: Learning an Iterative Level Generator Using a Small Dataset

no code implementations21 Feb 2022 Matthew Siper, Ahmed Khalifa, Julian Togelius

The Path of Destruction method, as we call it, views level generation as repair; levels are created by iteratively repairing from a random starting level.

Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning

1 code implementation8 Feb 2022 Bryon Tjanaka, Matthew C. Fontaine, Julian Togelius, Stefanos Nikolaidis

Training can then be viewed as a quality diversity (QD) optimization problem, where we search for a collection of performant policies that are diverse with respect to quantified behavior.

Diversity reinforcement-learning +1

Illuminating Diverse Neural Cellular Automata for Level Generation

2 code implementations12 Sep 2021 Sam Earle, Justin Snider, Matthew C. Fontaine, Stefanos Nikolaidis, Julian Togelius

We present a method of generating diverse collections of neural cellular automata (NCA) to design video game levels.


Self-Referential Quality Diversity Through Differential Map-Elites

no code implementations11 Jul 2021 Tae Jong Choi, Julian Togelius

Differential MAP-Elites is a novel algorithm that combines the illumination capacity of CVT-MAP-Elites with the continuous-space optimization capacity of Differential Evolution.


An Evolutionary Algorithm for Task Scheduling in Crowdsourced Software Development

no code implementations5 Jul 2021 Razieh Saremi, Hardik Yagnik, Julian Togelius, Ye Yang, Guenther Ruhe

In a competitive crowdsourcing marketplace, competition for shared worker resources from multiple simultaneously open tasks adds another layer of uncertainty to the potential outcomes of software crowdsourcing.


Physics-informed attention-based neural network for solving non-linear partial differential equations

no code implementations17 May 2021 Ruben Rodriguez-Torrado, Pablo Ruiz, Luis Cueto-Felgueroso, Michael Cerny Green, Tyler Friesen, Sebastien Matringe, Julian Togelius

PINNs are based on simple architectures, and learn the behavior of complex physical systems by optimizing the network parameters to minimize the residual of the underlying PDE.

Learning Controllable Content Generators

1 code implementation6 May 2021 Sam Earle, Maria Edwards, Ahmed Khalifa, Philip Bontrager, Julian Togelius

It has recently been shown that reinforcement learning can be used to train generators capable of producing high-quality game levels, with quality defined in terms of some user-specified heuristic.

The AI Settlement Generation Challenge in Minecraft: First Year Report

no code implementations27 Mar 2021 Christoph Salge, Michael Cerny Green, Rodrigo Canaan, Filip Skwarski, Rafael Fritsch, Adrian Brightmoore, Shaofang Ye, Changxing Cao, Julian Togelius

This article outlines what we learned from the first year of the AI Settlement Generation Competition in Minecraft, a competition about producing AI programs that can generate interesting settlements in Minecraft for an unseen map.

Game Mechanic Alignment Theory and Discovery

no code implementations20 Feb 2021 Michael Cerny Green, Ahmed Khalifa, Philip Bontrager, Rodrigo Canaan, Julian Togelius

We present a new concept called Game Mechanic Alignment theory as a way to organize game mechanics through the lens of systemic rewards and agential motivations.

Model-free Neural Counterfactual Regret Minimization with Bootstrap Learning

no code implementations3 Dec 2020 Weiming Liu, Bin Li, Julian Togelius

Experimental results show that Neural ReCFR-B is competitive with the state-of-the-art neural CFR algorithms at a much lower training cost.


Reinforcement Learning with Dual-Observation for General Video Game Playing

1 code implementation11 Nov 2020 Chengpeng Hu, Ziqi Wang, Tianye Shu, Hao Tong, Julian Togelius, Xin Yao, Jialin Liu

Our proposed technique is implemented with three state-of-the-art reinforcement learning algorithms and tested on the game set of the 2020 General Video Game AI Learning Competition.

Decision Making reinforcement-learning +1

Video Game Level Repair via Mixed Integer Linear Programming

1 code implementation13 Oct 2020 Hejia Zhang, Matthew C. Fontaine, Amy K. Hoover, Julian Togelius, Bistra Dilkina, Stefanos Nikolaidis

Recent advancements in procedural content generation via machine learning enable the generation of video-game levels that are aesthetically similar to human-authored examples.

Generative Adversarial Network

Deep Learning for Procedural Content Generation

no code implementations9 Oct 2020 Jialin Liu, Sam Snodgrass, Ahmed Khalifa, Sebastian Risi, Georgios N. Yannakakis, Julian Togelius

This article surveys the various deep learning methods that have been applied to generate game content directly or indirectly, discusses deep learning methods that could be used for content generation purposes but are rarely used today, and envisages some limitations and potential future directions of deep learning for procedural content generation.

Mixed-Initiative Level Design with RL Brush

1 code implementation6 Aug 2020 Omar Delarosa, Hang Dong, Mindy Ruan, Ahmed Khalifa, Julian Togelius

This paper introduces RL Brush, a level-editing tool for tile-based games designed for mixed-initiative co-creation.

reinforcement-learning Reinforcement Learning (RL)

Co-generation of game levels and game-playing agents

1 code implementation16 Jul 2020 Aaron Dharna, Julian Togelius, L. B. Soros

This paper introduces a POET-Inspired Neuroevolutionary System for KreativitY (PINSKY) in games, which co-generates levels for multiple video games and agents that play them.

Artificial Life

Multi-Stage Transfer Learning with an Application to Selection Process

no code implementations1 Jun 2020 Andre Mendes, Julian Togelius, Leandro dos Santos Coelho

In this work, we proposed a \textit{Multi-StaGe Transfer Learning} (MSGTL) approach that uses knowledge from simple classifiers trained in early stages to improve the performance of classifiers in the latter stages.

Transfer Learning

Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning

no code implementations26 May 2020 Vanessa Volz, Niels Justesen, Sam Snodgrass, Sahar Asadi, Sami Purmonen, Christoffer Holmgård, Julian Togelius, Sebastian Risi

Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically.

BIG-bench Machine Learning

Multi-Objective level generator generation with Marahel

1 code implementation17 May 2020 Ahmed Khalifa, Julian Togelius

This paper introduces a new system to design constructive level generators by searching the space of constructive level generators defined by Marahel language.

Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners

1 code implementation28 Apr 2020 Rodrigo Canaan, Xianbo Gao, Youjin Chung, Julian Togelius, Andy Nealen, Stefan Menzel

Hanabi is a cooperative game that challenges exist-ing AI techniques due to its focus on modeling the mental states ofother players to interpret and predict their behavior.

Generating and Adapting to Diverse Ad-Hoc Cooperation Agents in Hanabi

1 code implementation28 Apr 2020 Rodrigo Canaan, Xianbo Gao, Julian Togelius, Andy Nealen, Stefan Menzel

In this game, coordinated groups of players can leverage pre-established conventions to great effect, but playing in an ad-hoc setting requires agents to adapt to its partner's strategies with no previous coordination.


Designer Modeling through Design Style Clustering

1 code implementation3 Apr 2020 Alberto Alvarez, Jose Font, Julian Togelius

We propose modeling designer style in mixed-initiative game content creation tools as archetypical design traces.


Adversarial Encoder-Multi-Task-Decoder for Multi-Stage Processes

no code implementations15 Mar 2020 Andre Mendes, Julian Togelius, Leandro dos Santos Coelho

We also introduce a sequence constraint in the output of an MLSSL classifier to guarantee the sequential pattern in the predictions.

Decoder Medical Diagnosis +1

Unified Multi-Domain Learning and Data Imputation using Adversarial Autoencoder

no code implementations15 Mar 2020 Andre Mendes, Julian Togelius, Leandro dos Santos Coelho

We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) to improve performance for classification and regression tasks in different domains.

Imputation Multi-Task Learning

Interactive Constrained MAP-Elites: Analysis and Evaluation of the Expressiveness of the Feature Dimensions

1 code implementation6 Mar 2020 Alberto Alvarez, Steve Dahlskog, Jose Font, Julian Togelius

We propose the Interactive Constrained MAP-Elites, a quality-diversity solution for game content generation, implemented as a new feature of the Evolutionary Dungeon Designer: a mixed-initiative co-creativity tool for designing dungeons.


Learning to Generate Levels From Nothing

1 code implementation12 Feb 2020 Philip Bontrager, Julian Togelius

Unlike previous approaches to procedural content generation, Generative Playing Networks are end-to-end differentiable and do not require human-designed examples or domain knowledge.

Image Generation

Mech-Elites: Illuminating the Mechanic Space of GVGAI

no code implementations11 Feb 2020 M Charity, Michael Cerny Green, Ahmed Khalifa, Julian Togelius

This paper introduces a fully automatic method of mechanic illumination for general video game level generation.

Mario Level Generation From Mechanics Using Scene Stitching

no code implementations7 Feb 2020 Michael Cerny Green, Luvneesh Mugrai, Ahmed Khalifa, Julian Togelius

This paper presents a level generation method for Super Mario by stitching together pre-generated "scenes" that contain specific mechanics, using mechanic-sequences from agent playthroughs as input specifications.

Rotation, Translation, and Cropping for Zero-Shot Generalization

1 code implementation27 Jan 2020 Chang Ye, Ahmed Khalifa, Philip Bontrager, Julian Togelius

Deep Reinforcement Learning (DRL) has shown impressive performance on domains with visual inputs, in particular various games.

Reinforcement Learning (RL) Translation +1

Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space

6 code implementations5 Dec 2019 Matthew C. Fontaine, Julian Togelius, Stefanos Nikolaidis, Amy K. Hoover

Results from experiments based on standard continuous optimization benchmarks show that CMA-ME finds better-quality solutions than MAP-Elites; similarly, results on the strategic game Hearthstone show that CMA-ME finds both a higher overall quality and broader diversity of strategies than both CMA-ES and MAP-Elites.


Increasing Generality in Machine Learning through Procedural Content Generation

no code implementations29 Nov 2019 Sebastian Risi, Julian Togelius

Procedural Content Generation (PCG) refers to the practice, in videogames and other games, of generating content such as levels, quests, or characters algorithmically.

BIG-bench Machine Learning

Bootstrapping Conditional GANs for Video Game Level Generation

no code implementations3 Oct 2019 Ruben Rodriguez Torrado, Ahmed Khalifa, Michael Cerny Green, Niels Justesen, Sebastian Risi, Julian Togelius

Theresults demonstrate that the new approach does not only gen-erate a larger number of levels that are playable but also gen-erates fewer duplicate levels compared to a standard GAN.

Image Generation

Automatic Critical Mechanic Discovery Using Playtraces in Video Games

no code implementations6 Sep 2019 Michael Cerny Green, Ahmed Khalifa, Gabriella A. B. Barros, Tiago Machado, Julian Togelius

In a user study, human-identified mechanics are compared against system-identified critical mechanics to verify alignment between humans and the system.

The Many AI Challenges of Hearthstone

no code implementations15 Jul 2019 Amy K. Hoover, Julian Togelius, Scott Lee, Fernando De Mesentier Silva

Games have benchmarked AI methods since the inception of the field, with classic board games such as Chess and Go recently leaving room for video games with related yet different sets of challenges.

Board Games Card Games

Procedural Content Generation through Quality Diversity

1 code implementation9 Jul 2019 Daniele Gravina, Ahmed Khalifa, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis

Quality-diversity (QD) algorithms search for a set of good solutions which cover a space as defined by behavior metrics.

Diversity Evolutionary Algorithms

Diverse Agents for Ad-Hoc Cooperation in Hanabi

no code implementations8 Jul 2019 Rodrigo Canaan, Julian Togelius, Andy Nealen, Stefan Menzel

In complex scenarios where a model of other actors is necessary to predict and interpret their actions, it is often desirable that the model works well with a wide variety of previously unknown actors.


Pitako -- Recommending Game Design Elements in Cicero

no code implementations8 Jul 2019 Tiago Machado, Dan Gopstein, Andy Nealen, Julian Togelius

In this paper, we introduce Pitako1, a tool that applies the Recommender System concept to assist humans in creative tasks.

Game Design Recommendation Systems

Evolving the Hearthstone Meta

no code implementations2 Jul 2019 Fernando de Mesentier Silva, Rodrigo Canaan, Scott Lee, Matthew C. Fontaine, Julian Togelius, Amy K. Hoover

Balancing an ever growing strategic game of high complexity, such as Hearthstone is a complex task.

Advanced Cauchy Mutation for Differential Evolution in Numerical Optimization

no code implementations1 Jul 2019 Tae Jong Choi, Julian Togelius, Yun-Gyung Cheong

The method monitors the results of each individual in the selection operator and performs the Cauchy mutation on consecutively failed individuals, which generates mutant vectors by perturbing the best individual with the Cauchy distribution.

Evolutionary Algorithms

General Video Game Rule Generation

no code implementations12 Jun 2019 Ahmed Khalifa, Michael Cerny Green, Diego Perez-Liebana, Julian Togelius

We introduce the General Video Game Rule Generation problem, and the eponymous software framework which will be used in a new track of the General Video Game AI (GVGAI) competition.

ELIMINATION from Design to Analysis

no code implementations15 May 2019 Ahmed Khalifa, Dan Gopstein, Julian Togelius

Elimination is a word puzzle game for browsers and mobile devices, where all levels are generated by a constrained evolutionary algorithm with no human intervention.

Generative Design in Minecraft: Chronicle Challenge

no code implementations14 May 2019 Christoph Salge, Christian Guckelsberger, Michael Cerny Green, Rodrigo Canaan, Julian Togelius

We introduce the Chronicle Challenge as an optional addition to the Settlement Generation Challenge in Minecraft.

Mapping Hearthstone Deck Spaces through MAP-Elites with Sliding Boundaries

1 code implementation24 Apr 2019 Matthew C. Fontaine, Scott Lee, L. B. Soros, Fernando De Mesentier Silva, Julian Togelius, Amy K. Hoover

Quality diversity (QD) algorithms such as MAP-Elites have emerged as a powerful alternative to traditional single-objective optimization methods.


Intentional Computational Level Design

1 code implementation18 Apr 2019 Ahmed Khalifa, Michael Cerny Green, Gabriella Barros, Julian Togelius

The procedural generation of levels and content in video games is a challenging AI problem.

Diversity Evolutionary Algorithms

Tree Search vs Optimization Approaches for Map Generation

5 code implementations27 Mar 2019 Debosmita Bhaumik, Ahmed Khalifa, Michael Cerny Green, Julian Togelius

We compare them on three different game level generation problems: Binary, Zelda, and Sokoban.

Evolutionary Algorithms

Leveling the Playing Field -- Fairness in AI Versus Human Game Benchmarks

no code implementations17 Mar 2019 Rodrigo Canaan, Christoph Salge, Julian Togelius, Andy Nealen

The extent to which these games benchmark consist of fair competition between human and AI is also a matter of debate.


AAAI-2019 Workshop on Games and Simulations for Artificial Intelligence

no code implementations6 Mar 2019 Marwan Mattar, Roozbeh Mottaghi, Julian Togelius, Danny Lange

This volume represents the accepted submissions from the AAAI-2019 Workshop on Games and Simulations for Artificial Intelligence held on January 29, 2019 in Honolulu, Hawaii, USA.

AlphaStar: An Evolutionary Computation Perspective

1 code implementation5 Feb 2019 Kai Arulkumaran, Antoine Cully, Julian Togelius

In January 2019, DeepMind revealed AlphaStar to the world-the first artificial intelligence (AI) system to beat a professional player at the game of StarCraft II-representing a milestone in the progress of AI.

Diversity Reinforcement Learning (RL) +1

Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning

3 code implementations4 Feb 2019 Arthur Juliani, Ahmed Khalifa, Vincent-Pierre Berges, Jonathan Harper, Ervin Teng, Hunter Henry, Adam Crespi, Julian Togelius, Danny Lange

Unlike other benchmarks such as the Arcade Learning Environment, evaluation of agent performance in Obstacle Tower is based on an agent's ability to perform well on unseen instances of the environment.

Atari Games Board Games

DATA Agent

no code implementations28 Sep 2018 Michael Cerny Green, Gabriella A. B. Barros, Antonios Liapis, Julian Togelius

This paper introduces DATA Agent, a system which creates murder mystery adventures from open data.

Game Design

Evolving Agents for the Hanabi 2018 CIG Competition

no code implementations26 Sep 2018 Rodrigo Canaan, Haotian Shen, Ruben Rodriguez Torrado, Julian Togelius, Andy Nealen, Stefan Menzel

Hanabi is a cooperative card game with hidden information that has won important awards in the industry and received some recent academic attention.

Towards Game-based Metrics for Computational Co-creativity

no code implementations26 Sep 2018 Rodrigo Canaan, Stefan Menzel, Julian Togelius, Andy Nealen

We propose the following question: what game-like interactive system would provide a good environment for measuring the impact and success of a co-creative, cooperative agent?

A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking

1 code implementation9 Sep 2018 Matthew Stephenson, Damien Anderson, Ahmed Khalifa, John Levine, Jochen Renz, Julian Togelius, Christoph Salge

This paper introduces an information-theoretic method for selecting a subset of problems which gives the most information about a group of problem-solving algorithms.

Benchmarking Game Design

Generating Levels That Teach Mechanics

1 code implementation18 Jul 2018 Michael Cerny Green, Ahmed Khalifa, Gabriella A. B. Barros, Andy Nealen, Julian Togelius

The automatic generation of game tutorials is a challenging AI problem.

Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation

1 code implementation28 Jun 2018 Niels Justesen, Ruben Rodriguez Torrado, Philip Bontrager, Ahmed Khalifa, Julian Togelius, Sebastian Risi

However, when neural networks are trained in a fixed environment, such as a single level in a video game, they will usually overfit and fail to generalize to new levels.

Clustering Dimensionality Reduction +2

Talakat: Bullet Hell Generation through Constrained Map-Elites

no code implementations12 Jun 2018 Ahmed Khalifa, Scott Lee, Andy Nealen, Julian Togelius

We describe a search-based approach to generating new levels for bullet hell games, which are action games characterized by and requiring avoidance of a very large amount of projectiles.

Deep Reinforcement Learning for General Video Game AI

2 code implementations6 Jun 2018 Ruben Rodriguez Torrado, Philip Bontrager, Julian Togelius, Jialin Liu, Diego Perez-Liebana

In this paper, we describe how we interface GVGAI to the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems.

Atari Games Benchmarking +3

Playing Atari with Six Neurons

1 code implementation4 Jun 2018 Giuseppe Cuccu, Julian Togelius, Philippe Cudre-Mauroux

Deep reinforcement learning, applied to vision-based problems like Atari games, maps pixels directly to actions; internally, the deep neural network bears the responsibility of both extracting useful information and making decisions based on it.

Atari Games Decision Making +3

New And Surprising Ways to Be Mean. Adversarial NPCs with Coupled Empowerment Minimisation

no code implementations4 Jun 2018 Christian Guckelsberger, Christoph Salge, Julian Togelius

Creating Non-Player Characters (NPCs) that can react robustly to unforeseen player behaviour or novel game content is difficult and time-consuming.

Data-driven Design: A Case for Maximalist Game Design

no code implementations30 May 2018 Gabriella A. B. Barros, Michael Cerny Green, Antonios Liapis, Julian Togelius

Maximalism in art refers to drawing on and combining multiple different sources for art creation, embracing the resulting collisions and heterogeneity.

Game Design

"Press Space to Fire": Automatic Video Game Tutorial Generation

no code implementations30 May 2018 Michael Cerny Green, Ahmed Khalifa, Gabriella A. B. Barros, Julian Togelius

We propose the problem of tutorial generation for games, i. e. to generate tutorials which can teach players to play games, as an AI problem.

Generative Design in Minecraft (GDMC), Settlement Generation Competition

no code implementations27 Mar 2018 Christoph Salge, Michael Cerny Green, Rodrigo Canaan, Julian Togelius

This paper introduces the settlement generation competition for Minecraft, the first part of the Generative Design in Minecraft challenge.

General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms

1 code implementation28 Feb 2018 Diego Perez-Liebana, Jialin Liu, Ahmed Khalifa, Raluca D. Gaina, Julian Togelius, Simon M. Lucas

In 2014, The General Video Game AI (GVGAI) competition framework was created and released with the purpose of providing researchers a common open-source and easy to use platform for testing their AI methods with potentially infinity of games created using Video Game Description Language (VGDL).

Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristics

no code implementations19 Feb 2018 Christoffer Holmgård, Michael Cerny Green, Antonios Liapis, Julian Togelius

This paper describes a method for generative player modeling and its application to the automatic testing of game content using archetypal player models called procedural personas.

Deceptive Games

no code implementations31 Jan 2018 Damien Anderson, Matthew Stephenson, Julian Togelius, Christian Salge, John Levine, Jochen Renz

Deceptive games are games where the reward structure or other aspects of the game are designed to lead the agent away from a globally optimal policy.

Deep Interactive Evolution

1 code implementation24 Jan 2018 Philip Bontrager, Wending Lin, Julian Togelius, Sebastian Risi

The main insight in this paper is that a GAN trained on a specific target domain can act as a compact and robust genotype-to-phenotype mapping (i. e. most produced phenotypes do resemble valid domain artifacts).

Image Generation valid

Deep Learning for Video Game Playing

no code implementations25 Aug 2017 Niels Justesen, Philip Bontrager, Julian Togelius, Sebastian Risi

In this article, we review recent Deep Learning advances in the context of how they have been applied to play different types of video games such as first-person shooters, arcade games, and real-time strategy games.

BIG-bench Machine Learning Real-Time Strategy Games

Autoencoder-augmented Neuroevolution for Visual Doom Playing

no code implementations12 Jul 2017 Samuel Alvernaz, Julian Togelius

Neuroevolution has proven effective at many reinforcement learning tasks, but does not seem to scale well to high-dimensional controller representations, which are needed for tasks where the input is raw pixel data.

reinforcement-learning Reinforcement Learning (RL)

DeepMasterPrints: Generating MasterPrints for Dictionary Attacks via Latent Variable Evolution

no code implementations21 May 2017 Philip Bontrager, Aditi Roy, Julian Togelius, Nasir Memon, Arun Ross

The proposed method, referred to as Latent Variable Evolution, is based on training a Generative Adversarial Network on a set of real fingerprint images.

Generative Adversarial Network


no code implementations9 May 2017 Ahmed Khalifa, Gabriella A. B. Barros, Julian Togelius

DeepTingle is a text prediction and classification system trained on the collected works of the renowned fantastic gay erotica author Chuck Tingle.

General Classification Translation

Evolving Game Skill-Depth using General Video Game AI Agents

no code implementations18 Mar 2017 Jialin Liu, Julian Togelius, Diego Perez-Liebana, Simon M. Lucas

The space of possible parameter settings can be seen as a search space, and we can therefore use a Random Mutation Hill Climbing algorithm or other search methods to find the parameter settings that induce the best games.

Procedural Content Generation via Machine Learning (PCGML)

no code implementations2 Feb 2017 Adam Summerville, Sam Snodgrass, Matthew Guzdial, Christoffer Holmgård, Amy K. Hoover, Aaron Isaksen, Andy Nealen, Julian Togelius

This survey explores Procedural Content Generation via Machine Learning (PCGML), defined as the generation of game content using machine learning models trained on existing content.

BIG-bench Machine Learning Card Games +2

AI Researchers, Video Games Are Your Friends!

no code implementations6 Dec 2016 Julian Togelius

If you are an artificial intelligence researcher, you should look to video games as ideal testbeds for the work you do.

The Case for a Mixed-Initiative Collaborative Neuroevolution Approach

no code implementations5 Aug 2014 Sebastian Risi, Jinhong Zhang, Rasmus Taarnby, Peter Greve, Jan Piskur, Antonios Liapis, Julian Togelius

It is clear that the current attempts at using algorithms to create artificial neural networks have had mixed success at best when it comes to creating large networks and/or complex behavior.

Common Sense Reasoning Game Design +1

Active Player Modelling

no code implementations10 Dec 2013 Julian Togelius, Noor Shaker, Georgios N. Yannakakis

We further hypothesise that this form of curiosity is symmetric, and therefore that games that explore their players based on the principles of active learning will turn out to select game configurations that are interesting to the player that is being explored.

Active Learning

Measuring Intelligence through Games

no code implementations6 Sep 2011 Tom Schaul, Julian Togelius, Jürgen Schmidhuber

Artificial general intelligence (AGI) refers to research aimed at tackling the full problem of artificial intelligence, that is, create truly intelligent agents.

Motion Planning

Cannot find the paper you are looking for? You can Submit a new open access paper.