no code implementations • 23 May 2023 • Sumeet Batra, Bryon Tjanaka, Matthew C. Fontaine, Aleksei Petrenko, Stefanos Nikolaidis, Gaurav Sukhatme
However, recent advances in high-throughput, massively parallelized robotic simulators have opened the door for algorithms that can take advantage of such parallelism, and it is unclear how to scale existing off-policy QD-RL methods to these new data-rich regimes.
1 code implementation • 10 May 2023 • Yulun Zhang, Matthew C. Fontaine, Varun Bhatt, Stefanos Nikolaidis, Jiaoyang Li
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.
no code implementations • 26 Apr 2023 • Varun Bhatt, Heramb Nemlekar, Matthew C. Fontaine, Bryon Tjanaka, Hejia Zhang, Ya-Chuan Hsu, Stefanos Nikolaidis
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.
1 code implementation • 1 Mar 2023 • Bryon Tjanaka, Matthew C. Fontaine, David H. Lee, Yulun Zhang, Nivedit Reddy Balam, Nathaniel Dennler, Sujay S. Garlanka, Nikitas Dimitri Klapsis, Stefanos Nikolaidis
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.
no code implementations • 9 Dec 2022 • Shivin Dass, Karl Pertsch, Hejia Zhang, Youngwoon Lee, Joseph J. Lim, Stefanos Nikolaidis
Large-scale data is an essential component of machine learning as demonstrated in recent advances in natural language processing and computer vision research.
1 code implementation • 6 Oct 2022 • Bryon Tjanaka, Matthew C. Fontaine, David H. Lee, Aniruddha Kalkar, Stefanos Nikolaidis
Pre-training a diverse set of neural network controllers in simulation has enabled robots to adapt online to damage in robot locomotion tasks.
no code implementations • 4 Aug 2022 • Yilei Zeng, Jiali Duan, Yang Li, Emilio Ferrara, Lerrel Pinto, C. -C. Jay Kuo, Stefanos Nikolaidis
In this work, we guide the curriculum reinforcement learning results towards a preferred performance level that is neither too hard nor too easy via learning from the human decision process.
no code implementations • 20 Jun 2022 • Ya-Chuan Hsu, Matthew C. Fontaine, Sam Earle, Maria Edwards, Julian Togelius, Stefanos Nikolaidis
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.
no code implementations • 9 Jun 2022 • Varun Bhatt, Bryon Tjanaka, Matthew C. Fontaine, Stefanos Nikolaidis
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.
1 code implementation • 22 May 2022 • Matthew C. Fontaine, Stefanos Nikolaidis
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.
no code implementations • 12 Apr 2022 • Aniruddh G. Puranic, Jyotirmoy V. Deshmukh, Stefanos Nikolaidis
In the learning from demonstration (LfD) paradigm, understanding and evaluating the demonstrated behaviors plays a critical role in extracting control policies for robots.
1 code implementation • 8 Feb 2022 • Bryon Tjanaka, Matthew C. Fontaine, Julian Togelius, Stefanos Nikolaidis
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.
1 code implementation • 7 Dec 2021 • Yulun Zhang, Matthew C. Fontaine, Amy K. Hoover, Stefanos Nikolaidis
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.
2 code implementations • 12 Sep 2021 • Sam Earle, Justin Snider, Matthew C. Fontaine, Stefanos Nikolaidis, Julian Togelius
We present a method of generating diverse collections of neural cellular automata (NCA) to design video game levels.
2 code implementations • 21 Jun 2021 • Matthew C. Fontaine, Ya-Chuan Hsu, Yulun Zhang, Bryon Tjanaka, Stefanos Nikolaidis
When studying robots collaborating with humans, much of the focus has been on robot policies that coordinate fluently with human teammates in collaborative tasks.
2 code implementations • NeurIPS 2021 • 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 function but are also diverse with respect to a set of specified measure functions.
no code implementations • 15 Feb 2021 • Aniruddh G. Puranic, Jyotirmoy V. Deshmukh, Stefanos Nikolaidis
Learning-from-demonstrations is an emerging paradigm to obtain effective robot control policies for complex tasks via reinforcement learning without the need to explicitly design reward functions.
1 code implementation • 13 Oct 2020 • Hejia Zhang, Matthew C. Fontaine, Amy K. Hoover, Julian Togelius, Bistra Dilkina, Stefanos Nikolaidis
Recent advancements in procedural content generation via machine learning enable the generation of video-game levels that are aesthetically similar to human-authored examples.
1 code implementation • 11 Jul 2020 • Matthew C. Fontaine, Ruilin Liu, Ahmed Khalifa, Jignesh Modi, Julian Togelius, Amy K. Hoover, Stefanos Nikolaidis
Generative adversarial networks (GANs) are quickly becoming a ubiquitous approach to procedurally generating video game levels.
no code implementations • 13 Dec 2019 • Yifang Chen, Alex Cuellar, Haipeng Luo, Jignesh Modi, Heramb Nemlekar, Stefanos Nikolaidis
We introduce a Multi-Armed Bandit algorithm with fairness constraints, where fairness is defined as a minimum rate that a task or a resource is assigned to a user.
6 code implementations • 5 Dec 2019 • Matthew C. Fontaine, Julian Togelius, Stefanos Nikolaidis, Amy K. Hoover
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.
no code implementations • 25 Nov 2019 • Hejia Zhang, Jie Zhong, Stefanos Nikolaidis
Building upon this theory of language for action, we propose a system for understanding and executing demonstrated action sequences from full-length, real-world cooking videos on the web.
no code implementations • 30 Jun 2019 • Houston Claure, Yifang Chen, Jignesh Modi, Malte Jung, Stefanos Nikolaidis
How should a robot that collaborates with multiple people decide upon the distribution of resources (e. g. social attention, or parts needed for an assembly)?
no code implementations • 29 Sep 2018 • Hejia Zhang, Eric Heiden, Stefanos Nikolaidis, Joseph J. Lim, Gaurav S. Sukhatme
Personal robots assisting humans must perform complex manipulation tasks that are typically difficult to specify in traditional motion planning pipelines, where multiple objectives must be met and the high-level context be taken into consideration.
no code implementations • 12 Jan 2018 • Min Chen, Stefanos Nikolaidis, Harold Soh, David Hsu, Siddhartha Srinivasa
The trust-POMDP model provides a principled approach for the robot to (i) infer the trust of a human teammate through interaction, (ii) reason about the effect of its own actions on human trust, and (iii) choose actions that maximize team performance over the long term.
no code implementations • 24 May 2014 • Stefanos Nikolaidis, Keren Gu, Ramya Ramakrishnan, Julie Shah
We present a framework for learning human user models from joint-action demonstrations that enables the robot to compute a robust policy for a collaborative task with a human.