121 citations · 251 across the 23 of their papers we have counts for
25 papers
Optimization of Edge Directions and Weights for Mixed Guidance Graphs in Lifelong Multi-Agent Path Finding
Yulun Zhang, Varun Bhatt, Matthew C. Fontaine +2
Multi-Agent Path Finding (MAPF) aims to move agents from their start to goal vertices on a graph. Lifelong MAPF (LMAPF) continuously assigns new goals to agents as they complete cu…
Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces
Bryon Tjanaka, Henry Chen, Matthew C. Fontaine +1
Quality diversity (QD) optimization searches for a collection of solutions that optimize an objective while attaining diverse outputs of a user-specified, vector-valued measure fun…
QD-MAPPER: A Quality Diversity Framework to Automatically Evaluate Multi-Agent Path Finding Algorithms in Diverse Maps
Cheng Qian, Yulun Zhang, Varun Bhatt +3
We use the Quality Diversity (QD) algorithm with Neural Cellular Automata (NCA) to automatically evaluate Multi-Agent Path Finding (MAPF) algorithms by generating diverse maps. Pre…
Quality-Diversity Generative Sampling for Learning with Synthetic Data
Allen Chang, Matthew C. Fontaine, Serena Booth +2
Generative models can serve as surrogates for some real data sources by creating synthetic training datasets, but in doing so they may transfer biases to downstream tasks. We focus…
Density Descent for Diversity Optimization
David H. Lee, Anishalakshmi V. Palaparthi, Matthew C. Fontaine +2
Diversity optimization seeks to discover a set of solutions that elicit diverse features. Prior work has proposed Novelty Search (NS), which, given a current set of solutions, seek…
Arbitrarily Scalable Environment Generators via Neural Cellular Automata
Yulun Zhang, Matthew C. Fontaine, Varun Bhatt +2
We study the problem of generating arbitrarily large environments to improve the throughput of multi-robot systems. Prior work proposes Quality Diversity (QD) algorithms as an effe…
Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning
Sumeet Batra, Bryon Tjanaka, Matthew C. Fontaine +3
Training generally capable agents that thoroughly explore their environment and learn new and diverse skills is a long-term goal of robot learning. Quality Diversity Reinforcement…
Multi-Robot Coordination and Layout Design for Automated Warehousing
Yulun Zhang, Matthew C. Fontaine, Varun Bhatt +2
With the rapid progress in Multi-Agent Path Finding (MAPF), researchers have studied how MAPF algorithms can be deployed to coordinate hundreds of robots in large automated warehou…
pyribs: A Bare-Bones Python Library for Quality Diversity Optimization
Bryon Tjanaka, Matthew C. Fontaine, David H. Lee +6
Recent years have seen a rise in the popularity of quality diversity (QD) optimization, a branch of optimization that seeks to find a collection of diverse, high-performing solutio…
Surrogate Assisted Generation of Human-Robot Interaction Scenarios
Varun Bhatt, Heramb Nemlekar, Matthew C. Fontaine +4
As human-robot interaction (HRI) systems advance, so does the difficulty of evaluating and understanding the strengths and limitations of these systems in different environments an…
Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealing
Bryon Tjanaka, Matthew C. Fontaine, David H. Lee +2
Pre-training a diverse set of neural network controllers in simulation has enabled robots to adapt online to damage in robot locomotion tasks. However, finding diverse, high-perfor…
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…
Deep Surrogate Assisted Generation of Environments
Varun Bhatt, Bryon Tjanaka, Matthew C. Fontaine +1
Recent progress in reinforcement learning (RL) has started producing generally capable agents that can solve a distribution of complex environments. These agents are typically test…
Covariance Matrix Adaptation MAP-Annealing
Matthew C. Fontaine, Stefanos Nikolaidis
Single-objective optimization algorithms search for the single highest-quality solution with respect to an objective. Quality diversity (QD) optimization algorithms, such as Covari…
Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning
Bryon Tjanaka, Matthew C. Fontaine, Julian Togelius +1
Consider the problem of training robustly capable agents. One approach is to generate a diverse collection of agent polices. Training can then be viewed as a quality diversity (QD)…
Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding
Yulun Zhang, Matthew C. Fontaine, Amy K. Hoover +1
We study the problem of efficiently generating high-quality and diverse content in games. Previous work on automated deckbuilding in Hearthstone shows that the quality diversity al…
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…
On the Importance of Environments in Human-Robot Coordination
Matthew C. Fontaine, Ya-Chuan Hsu, Yulun Zhang +2
When studying robots collaborating with humans, much of the focus has been on robot policies that coordinate fluently with human teammates in collaborative tasks. However, less emp…
Differentiable Quality Diversity
Matthew C. Fontaine, Stefanos Nikolaidis
Quality diversity (QD) is a growing branch of stochastic optimization research that studies the problem of generating an archive of solutions that maximize a given objective functi…
A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomy
Matthew Fontaine, Stefanos Nikolaidis
The growth of scale and complexity of interactions between humans and robots highlights the need for new computational methods to automatically evaluate novel algorithms and applic…
Video Game Level Repair via Mixed Integer Linear Programming
Hejia Zhang, Matthew C. Fontaine, Amy K. Hoover +3
Recent advancements in procedural content generation via machine learning enable the generation of video-game levels that are aesthetically similar to human-authored examples. Howe…
Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network
Matthew C. Fontaine, Ruilin Liu, Ahmed Khalifa +4
Generative adversarial networks (GANs) are quickly becoming a ubiquitous approach to procedurally generating video game levels. While GAN generated levels are stylistically similar…
Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space
Matthew C. Fontaine, Julian Togelius, Stefanos Nikolaidis +1
We focus on the challenge of finding a diverse collection of quality solutions on complex continuous domains. While quality diver-sity (QD) algorithms like Novelty Search with Loca…
Evolving the Hearthstone Meta
Fernando de Mesentier Silva, Rodrigo Canaan, Scott Lee +3
Balancing an ever growing strategic game of high complexity, such as Hearthstone is a complex task. The target of making strategies diverse and customizable results in a delicate i…