no code implementations • 2 Oct 2024 • Sam Earle, Samyak Parajuli, Andrzej Banburski-Fahey
Coding assistants are increasingly leveraged in game design, both generating code and making high-level plans.
no code implementations • 22 Aug 2024 • Sam Earle, Zehua Jiang, Julian Togelius
Procedural Content Generation via Reinforcement Learning (PCGRL) has been introduced as a means by which controllable designer agents can be trained based only on a set of computable metrics acting as a proxy for the level's quality and key characteristics.
no code implementations • 15 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.
no code implementations • 5 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.
no code implementations • 23 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.
no code implementations • 17 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.
no code implementations • 28 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.
no code implementations • 4 Dec 2023 • Sam Earle, M Charity, Dipika Rajesh, Mayu Wilson, Julian Togelius
We explore the generation of diverse environments using the Amorphous Fortress (AF) simulation framework.
no code implementations • 20 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.
no code implementations • 22 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.
1 code implementation • 1 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.
no code implementations • 29 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.
no code implementations • 11 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.
no code implementations • 17 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.
1 code implementation • 27 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.
no code implementations • 20 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.
2 code implementations • 12 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.
no code implementations • 10 May 2021 • Michael Cerny Green, Victoria Yen, Sam Earle, Dipika Rajesh, Maria Edwards, L. B. Soros
This paper introduces MicroRCT, a novel open source simulator inspired by the theme park sandbox game RollerCoaster Tycoon.
1 code implementation • 6 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.
no code implementations • 29 Jan 2020 • Sam Earle
We introduce gym-city, a Reinforcement Learning environment that uses SimCity 1's game engine to simulate an urban environment, wherein agents might seek to optimize one or a combination of any number of city-wide metrics, on gameboards of various sizes.
6 code implementations • 24 Jan 2020 • Ahmed Khalifa, Philip Bontrager, Sam Earle, Julian Togelius
We investigate how reinforcement learning can be used to train level-designing agents.