Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Racah, Evan"'
Autor:
Bronstein, Eli, Palatucci, Mark, Notz, Dominik, White, Brandyn, Kuefler, Alex, Lu, Yiren, Paul, Supratik, Nikdel, Payam, Mougin, Paul, Chen, Hongge, Fu, Justin, Abrams, Austin, Shah, Punit, Racah, Evan, Frenkel, Benjamin, Whiteson, Shimon, Anguelov, Dragomir
Publikováno v:
IEEE/RSJ international conference on intelligent robots and systems (IROS) 2022, pages 8652-8659
We demonstrate the first large-scale application of model-based generative adversarial imitation learning (MGAIL) to the task of dense urban self-driving. We augment standard MGAIL using a hierarchical model to enable generalization to arbitrary goal
Externí odkaz:
http://arxiv.org/abs/2210.09539
Autor:
Racah, Evan
Extraire une représentation de tous les facteurs de haut niveau de l'état d'un agent à partir d'informations sensorielles de bas niveau est une tâche importante, mais difficile, dans l'apprentissage automatique. Dans ce memoire, nous explorerons
Externí odkaz:
http://hdl.handle.net/1866/23788
Autor:
Racah, Evan, Chandar, Sarath
Unsupervised extraction of objects from low-level visual data is an important goal for further progress in machine learning. Existing approaches for representing objects without labels use structured generative models with static images. These method
Externí odkaz:
http://arxiv.org/abs/2007.09294
Deep model-based Reinforcement Learning (RL) has the potential to substantially improve the sample-efficiency of deep RL. While various challenges have long held it back, a number of papers have recently come out reporting success with deep model-bas
Externí odkaz:
http://arxiv.org/abs/2007.03158
Autor:
Racah, Evan, Pal, Christopher
Self-supervised methods, wherein an agent learns representations solely by observing the results of its actions, become crucial in environments which do not provide a dense reward signal or have labels. In most cases, such methods are used for pretra
Externí odkaz:
http://arxiv.org/abs/1906.11951
Autor:
Anand, Ankesh, Racah, Evan, Ozair, Sherjil, Bengio, Yoshua, Côté, Marc-Alexandre, Hjelm, R Devon
State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks. Learning such representations without supervision from rewards
Externí odkaz:
http://arxiv.org/abs/1906.08226
Autor:
Bhimji, Wahid, Farrell, Steven Andrew, Kurth, Thorsten, Paganini, Michela, Prabhat, Racah, Evan
There has been considerable recent activity applying deep convolutional neural nets (CNNs) to data from particle physics experiments. Current approaches on ATLAS/CMS have largely focussed on a subset of the calorimeter, and for identifying objects or
Externí odkaz:
http://arxiv.org/abs/1711.03573
Autor:
Kurth, Thorsten, Zhang, Jian, Satish, Nadathur, Mitliagkas, Ioannis, Racah, Evan, Patwary, Mostofa Ali, Malas, Tareq, Sundaram, Narayanan, Bhimji, Wahid, Smorkalov, Mikhail, Deslippe, Jack, Shiryaev, Mikhail, Sridharan, Srinivas, Prabhat, Dubey, Pradeep
This paper presents the first, 15-PetaFLOP Deep Learning system for solving scientific pattern classification problems on contemporary HPC architectures. We develop supervised convolutional architectures for discriminating signals in high-energy phys
Externí odkaz:
http://arxiv.org/abs/1708.05256
Autor:
Racah, Evan, Beckham, Christopher, Maharaj, Tegan, Kahou, Samira Ebrahimi, Prabhat, Pal, Christopher
Then detection and identification of extreme weather events in large-scale climate simulations is an important problem for risk management, informing governmental policy decisions and advancing our basic understanding of the climate system. Recent wo
Externí odkaz:
http://arxiv.org/abs/1612.02095
Autor:
Patwary, Md. Mostofa Ali, Satish, Nadathur Rajagopalan, Sundaram, Narayanan, Liu, Jialin, Sadowski, Peter, Racah, Evan, Byna, Suren, Tull, Craig, Bhimji, Wahid, Prabhat, Dubey, Pradeep
Computing $k$-Nearest Neighbors (KNN) is one of the core kernels used in many machine learning, data mining and scientific computing applications. Although kd-tree based $O(\log n)$ algorithms have been proposed for computing KNN, due to its inherent
Externí odkaz:
http://arxiv.org/abs/1607.08220