Search Results for author:
Found 21 papers, 16 papers with code
Quality-Diversity Generative Sampling for Learning with Synthetic Data
QDGS is a model-agnostic framework that uses prompt guidance to optimize a quality objective across measures of diversity for synthetically generated data, without fine-tuning the generative model.
Density Descent for Diversity Optimization
We propose Density Descent Search (DDS), an algorithm that explores the feature space via gradient descent on a continuous density estimate of the feature space that also provides stronger stability guarantee.
Arbitrarily Scalable Environment Generators via Neural Cellular Automata
We show that NCA environment generators maintain consistent, regularized patterns regardless of environment size, significantly enhancing the scalability of multi-robot systems in two different domains with up to 2, 350 robots.
Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning
Training generally capable agents that thoroughly explore their environment and learn new and diverse skills is a long-term goal of robot learning.
Multi-Robot Coordination and Layout Design for Automated Warehousing
We show that, even with state-of-the-art MAPF algorithms, commonly used human-designed layouts can lead to congestion for warehouses with large numbers of robots and thus have limited scalability.
Surrogate Assisted Generation of Human-Robot Interaction Scenarios
In the shared control teleoperation domain and a more complex shared workspace collaboration task, we show that surrogate assisted scenario generation efficiently synthesizes diverse datasets of challenging scenarios.
pyribs: A Bare-Bones Python Library for Quality Diversity Optimization
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 solutions to a given problem.
Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealing
Pre-training a diverse set of neural network controllers in simulation has enabled robots to adapt online to damage in robot locomotion tasks.
Generating Diverse Indoor Furniture Arrangements
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.
Deep Surrogate Assisted Generation of Environments
Results in two benchmark domains show that DSAGE significantly outperforms existing QD environment generation algorithms in discovering collections of environments that elicit diverse behaviors of a state-of-the-art RL agent and a planning agent.
Covariance Matrix Adaptation MAP-Annealing
Quality diversity (QD) optimization algorithms, such as Covariance Matrix Adaptation MAP-Elites (CMA-ME), search for a collection of solutions that are both high-quality with respect to an objective and diverse with respect to specified measure functions.
Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning
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.
Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding
In a Hearthstone deckbuilding case study, we show that our approach improves the sample efficiency of MAP-Elites and outperforms a model trained offline with random decks, as well as a linear surrogate model baseline, setting a new state-of-the-art for quality diversity approaches in automated Hearthstone deckbuilding.
Illuminating Diverse Neural Cellular Automata for Level Generation
We present a method of generating diverse collections of neural cellular automata (NCA) to design video game levels.
On the Importance of Environments in Human-Robot Coordination
When studying robots collaborating with humans, much of the focus has been on robot policies that coordinate fluently with human teammates in collaborative tasks.
Differentiable Quality Diversity
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 function but are also diverse with respect to a set of specified measure functions.
Video Game Level Repair via Mixed Integer Linear Programming
Recent advancements in procedural content generation via machine learning enable the generation of video-game levels that are aesthetically similar to human-authored examples.
Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network
Generative adversarial networks (GANs) are quickly becoming a ubiquitous approach to procedurally generating video game levels.
Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space
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.
Evolving the Hearthstone Meta
Balancing an ever growing strategic game of high complexity, such as Hearthstone is a complex task.
Mapping Hearthstone Deck Spaces through MAP-Elites with Sliding Boundaries
Quality diversity (QD) algorithms such as MAP-Elites have emerged as a powerful alternative to traditional single-objective optimization methods.
