Entity

Time filter

Source Type

Pittsburgh, PA, United States

Stolle M.,5000 Forbes Ave | Stolle M.,Google | Atkeson C.,5000 Forbes Ave
Autonomous Robots | Year: 2010

We present several algorithms that aim to advance the state-of-the-art in reinforcement learning and planning algorithms. One key idea is to transfer knowledge across problems by representing it using local features. This idea is used to speed up a dynamic programming based generalized policy iteration. We then present a control approach that uses a library of trajectories to establish a control law or policy. This approach is an alternative to methods for finding policies based on value functions using dynamic programming and also to using plans based on a single desired trajectory. Our method has the advantages of providing reasonable policies much faster than dynamic programming and providing more robust and global policies than following a single desired trajectory. Finally we show how local features can be used to transfer libraries of trajectories between similar problems. Transfer makes it useful to store special purpose behaviors in the library for solving tricky situations in new environments. By adapting the behaviors in the library, we increase the applicability of the behaviors. Our approach can be viewed as a method that allows planning algorithms to make use of special purpose behaviors/actions which are only applicablein certain situations.Results are shown for the "Labyrinth" marble maze and the Little Dog quadruped robot. The marble maze is a difficult task which requires both fast control as well as planning ahead. In the Little Dog terrain, a quadruped robot has to navigate quickly across rough terrain. © Springer Science+Business Media, LLC 2010. Source


Epting W.K.,5000 Forbes Ave | Gelb J.,5000 Forbes Ave | Litster S.,5000 Forbes Ave
Advanced Functional Materials | Year: 2012

The electrodes of a polymer electrolyte fuel cell (PEFC) are composite porous layers consisting of carbon and platinum nanoparticles and a polymer electrolyte binder. The proper composition and arrangement of these materials for fast reactant transport and high electrochemical activity is crucial to achieving high performance, long lifetimes, and low costs. Here, the microstructure of a PEFC electrode using nanometer-scale X-ray computed tomography (nano-CT) with a resolution of 50 nm is investigated. The nano-CT instrument obtains this resolution for the low-atomic-number catalyst support and binder using a combination of a Fresnel zone plate objective and Zernike phase contrast imaging. High-resolution, non-destructive imaging of the three-dimensional (3D) microstructures provides important new information on the size and form of the catalyst particle agglomerates and pore spaces. Transmission electron microscopy (TEM) and mercury intrusion porosimetry (MIP) is applied to evaluate the limits of the resolution and to verify the 3D reconstructions. The computational reconstructions and size distributions obtained with nano-CT can be used for evaluating electrode preparation, performing pore-scale simulations, and extracting effective morphological parameters for large-scale computational models. © 2012 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim. Source


Li N.,5000 Forbes Ave | Matsuda N.,5000 Forbes Ave | Cohen W.W.,5000 Forbes Ave | Koedinger K.R.,5000 Forbes Ave
Artificial Intelligence | Year: 2015

Building an intelligent agent that simulates human learning of math and science could potentially benefit both cognitive science, by contributing to the understanding of human learning, and artificial intelligence, by advancing the goal of creating human-level intelligence. However, constructing such a learning agent currently requires manual encoding of prior domain knowledge; in addition to being a poor model of human acquisition of prior knowledge, manual knowledge-encoding is both time-consuming and error-prone. Previous research has shown that one of the key factors that differentiates experts and novices is their different representations of knowledge. Experts view the world in terms of deep functional features, while novices view it in terms of shallow perceptual features. Moreover, since the performance of learning algorithms is sensitive to representation, the deep features are also important in achieving effective machine learning. In this paper, we present an efficient algorithm that acquires representation knowledge in the form of "deep features", and demonstrate its effectiveness in the domain of algebra as well as synthetic domains. We integrate this algorithm into a machine-learning agent, SimStudent, which learns procedural knowledge by observing a tutor solve sample problems, and by getting feedback while actively solving problems on its own. We show that learning "deep features" reduces the requirements for knowledge engineering. Moreover, we propose an approach that automatically discovers student models using the extended SimStudent. By fitting the discovered model to real student learning curve data, we show that it is a better student model than human-generated models, and demonstrate how the discovered model may be used to improve a tutoring system's instructional strategy. © 2014 Elsevier B.V. All rights reserved. Source

Discover hidden collaborations