papers

Publications (32)

cs.GR2024

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…

cs.LG2024

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…

cs.AI2023

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…

cs.LG2023

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…

cs.AI2025

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…

cs.AI2025

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…

cs.AI2024

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…

cs.AI2025

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…

cs.CL2024

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…

cs.AI2021

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…

cs.NE2024

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…

cs.HC2025

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…

cs.CL2024

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…

cs.AI2025

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…

cs.AI2025

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…

cs.NE2022

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…

cs.LG2020

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…

cs.NE2023

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…

cs.AI2023

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…

cs.AI2023

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…

cs.LG2022

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…

cs.CV2026

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…

cs.AI2026

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…

cs.HC2026

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…

cs.LG2021

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…

cs.LG2020

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…

cs.AI2025

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…

cs.AI2022

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…

cs.AI2025

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…

cs.AI2024

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…

cs.AI2023

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…

cs.AI2026

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…