Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Fontaine, Matthew C."'
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 on protecting quality and diversity when generating synthetic trainin
Externí odkaz:
http://arxiv.org/abs/2312.14369
Autor:
Lee, David H., Palaparthi, Anishalakshmi V., Fontaine, Matthew C., Tjanaka, Bryon, Nikolaidis, Stefanos
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, seeks to expand the set by finding points in areas of low density in the f
Externí odkaz:
http://arxiv.org/abs/2312.11331
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 effective method for optimizing the environments of automated warehouses.
Externí odkaz:
http://arxiv.org/abs/2310.18622
Autor:
Batra, Sumeet, Tjanaka, Bryon, Fontaine, Matthew C., Petrenko, Aleksei, Nikolaidis, Stefanos, Sukhatme, Gaurav
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 Learning (QD-RL) is an emerging research area that blends the best asp
Externí odkaz:
http://arxiv.org/abs/2305.13795
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 warehouses. While most works try to improve the throughput of such warehouses
Externí odkaz:
http://arxiv.org/abs/2305.06436
Autor:
Bhatt, Varun, Nemlekar, Heramb, Fontaine, Matthew C., Tjanaka, Bryon, Zhang, Hejia, Hsu, Ya-Chuan, Nikolaidis, Stefanos
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 and with different users. To this end, previous methods have algorithmic
Externí odkaz:
http://arxiv.org/abs/2304.13787
Autor:
Tjanaka, Bryon, Fontaine, Matthew C., Lee, David H., Zhang, Yulun, Balam, Nivedit Reddy, Dennler, Nathaniel, Garlanka, Sujay S., Klapsis, Nikitas Dimitri, Nikolaidis, Stefanos
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. To grow further, we believe the QD community fa
Externí odkaz:
http://arxiv.org/abs/2303.00191
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-performing controllers requires expensive network training and extensive tun
Externí odkaz:
http://arxiv.org/abs/2210.02622
Autor:
Hsu, Ya-Chuan, Fontaine, Matthew C., Earle, Sam, Edwards, Maria, Togelius, Julian, Nikolaidis, Stefanos
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 as the total price of all furniture in the room and the number of pie
Externí odkaz:
http://arxiv.org/abs/2206.10608
Recent progress in reinforcement learning (RL) has started producing generally capable agents that can solve a distribution of complex environments. These agents are typically tested on fixed, human-authored environments. On the other hand, quality d
Externí odkaz:
http://arxiv.org/abs/2206.04199