Publications (32)
DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft
Sam Earle, Filippos Kokkinos, Yuhe Nie +2
Procedural Content Generation (PCG) algorithms enable the automatic generation of complex and diverse artifacts. However, they don't provide high-level control over the generated c…
PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generators
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 computab…
Level Generation Through Large Language Models
Graham Todd, Sam Earle, Muhammad Umair Nasir +2
Large Language Models (LLMs) are powerful tools, capable of leveraging their training on natural language to write stories, generate code, and answer questions. But can they genera…
Pathfinding Neural Cellular Automata
Sam Earle, Ozlem Yildiz, Julian Togelius +1
Pathfinding makes up an important sub-component of a broad range of complex tasks in AI, such as robot path planning, transport routing, and game playing. While classical algorithm…
All Stories Are One Story: Emotional Arc Guided Procedural Game Level Generation
Yunge Wen, Chenliang Huang, Hangyu Zhou +5
The emotional arc is a universal narrative structure underlying stories across cultures and media -- an idea central to structuralist narratology, often encapsulated in the phrase…
Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games
Shouren Wang, Zehua Jiang, Fernando Sliva +2
Deep reinforcement learning (DRL) has effectively enhanced gameplay experiences and game design across various game genres. However, few studies on fighting game agents have focuse…
Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents
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…
ScriptDoctor: Automatic Generation of PuzzleScript Games via Large Language Models and Tree Search
Sam Earle, Ahmed Khalifa, Muhammad Umair Nasir +4
There is much interest in using large pre-trained models in Automatic Game Design (AGD), whether via the generation of code, assets, or more abstract conceptualization of design id…
Large Language Models and Games: A Survey and Roadmap
Roberto Gallotta, Graham Todd, Marvin Zammit +4
Recent years have seen an explosive increase in research on large language models (LLMs), and accompanying public engagement on the topic. While starting as a niche area within nat…
Exploring open-ended gameplay features with Micro RollerCoaster Tycoon
Michael Cerny Green, Victoria Yen, Sam Earle +3
This paper introduces MicroRCT, a novel open source simulator inspired by the theme park sandbox game RollerCoaster Tycoon. The goal in MicroRCT is to place rides and shops in an a…
LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization
Muhammad U. Nasir, Sam Earle, Christopher Cleghorn +2
Large Language Models (LLMs) have emerged as powerful tools capable of accomplishing a broad spectrum of tasks. Their abilities span numerous areas, and one area where they have ma…
DreamGarden: A Designer Assistant for Growing Games from a Single Prompt
Sam Earle, Samyak Parajuli, Andrzej Banburski-Fahey
Coding assistants are increasingly leveraged in game design, both generating code and making high-level plans. To what degree can these tools align with developer workflows, and wh…
Missed Connections: Lateral Thinking Puzzles for Large Language Models
Graham Todd, Tim Merino, Sam Earle +1
The Connections puzzle published each day by the New York Times tasks players with dividing a bank of sixteen words into four groups of four words that each relate to a common them…
A Markovian Framing of WaveFunctionCollapse for Procedurally Generating Aesthetically Complex Environments
Franklin Yiu, Mohan Lu, Nina Li +5
Procedural content generation often requires satisfying both designer-specified objectives and adjacency constraints implicitly imposed by the underlying tile set. To address the c…
Video Game Level Design as a Multi-Agent Reinforcement Learning Problem
Sam Earle, Zehua Jiang, Eugene Vinitsky +1
Procedural Content Generation via Reinforcement Learning (PCGRL) offers a method for training controllable level designer agents without the need for human datasets, using metrics…
Illuminating Diverse Neural Cellular Automata for Level Generation
Sam Earle, Justin Snider, Matthew C. Fontaine +2
We present a method of generating diverse collections of neural cellular automata (NCA) to design video game levels. While NCAs have so far only been trained via supervised learnin…
Using Fractal Neural Networks to Play SimCity 1 and Conway's Game of Life at Variable Scales
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 combi…
Evolutionary Machine Learning and Games
Julian Togelius, Ahmed Khalifa, Sam Earle +2
Evolutionary machine learning (EML) has been applied to games in multiple ways, and for multiple different purposes. Importantly, AI research in games is not only about playing gam…
Amorphous Fortress: Observing Emergent Behavior in Multi-Agent FSMs
M Charity, Dipika Rajesh, Sam Earle +1
We introduce a system called Amorphous Fortress -- an abstract, yet spatial, open-ended artificial life simulation. In this environment, the agents are represented as finite-state…
Controllable Path of Destruction
Matthew Siper, Sam Earle, Zehua Jiang +2
Path of Destruction (PoD) is a self-supervised method for learning iterative generators. The core idea is to produce a training set by destroying a set of artifacts, and for each d…
Generating Diverse Indoor Furniture Arrangements
Ya-Chuan Hsu, Matthew C. Fontaine, Sam Earle +3
We present a method for generating arrangements of indoor furniture from human-designed furniture layout data. Our method creates arrangements that target specified diversity, such…
Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes
Tim Merino, Sam Earle, Ryunosuke Iwai +2
We introduce Dream-Cubed, a large-scale dataset of Minecraft worlds at voxel resolution, and a family of models using cubes as powerful compositional units for efficient generation…
In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language Models
Sam Earle, Kai Arulkumaran, Andrew Dai +3
We are in the midst of large-scale industrial and academic efforts to automate the processes of scientific, technological and creative production through AI-driven assistants. Hist…
The Garden of Forking Paths: Narrative Arc-Conditioned Gameplay Planning
Yunge Wen, Chenliang Huang, Hangyu Zhou +5
Narrative archetypes (e.g., Hero's Journey, Three-act structure) provide universal story structures that resonate across cultures and media and are important for video game storyte…
Learning Controllable Content Generators
Sam Earle, Maria Edwards, Ahmed Khalifa +2
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-spe…
PCGRL: Procedural Content Generation via Reinforcement Learning
Ahmed Khalifa, Philip Bontrager, Sam Earle +1
We investigate how reinforcement learning can be used to train level-designing agents. This represents a new approach to procedural content generation in games, where level design…
Amorphous Fortress Online: Collaboratively Designing Open-Ended Multi-Agent AI and Game Environments
M Charity, Mayu Wilson, Steven Lee +3
This work introduces Amorphous Fortress Online -- a web-based platform where users can design petri-dish-like environments and games consisting of multi-agent AI characters. Users…
Learning Controllable 3D Level Generators
Zehua Jiang, Sam Earle, Michael Cerny Green +1
Procedural Content Generation via Reinforcement Learning (PCGRL) foregoes the need for large human-authored data-sets and allows agents to train explicitly on functional constraint…
PuzzleJAX: A Benchmark for Reasoning and Learning
Sam Earle, Graham Todd, Yuchen Li +5
We introduce PuzzleJAX, a GPU-accelerated puzzle game engine and description language designed to support rapid benchmarking of tree search, reinforcement learning, and LLM reasoni…
Making New Connections: LLMs as Puzzle Generators for The New York Times' Connections Word Game
Tim Merino, Sam Earle, Ryan Sudhakaran +2
The Connections puzzle is a word association game published daily by The New York Times (NYT). In this game, players are asked to find groups of four words that are connected by a…
Quality Diversity in the Amorphous Fortress (QD-AF): Evolving for Complexity in 0-Player Games
Sam Earle, M Charity, Dipika Rajesh +2
We explore the generation of diverse environments using the Amorphous Fortress (AF) simulation framework. AF defines a set of Finite State Machine (FSM) nodes and edges that can be…
PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning
In-Chang Baek, Sung-Hyun Kim, Sam Earle +4
Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-specific knowledge and human effort. In recent years, several studies have explored rew…