Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Venkatraman, Arun"'
Autor:
Spencer, Jonathan, Choudhury, Sanjiban, Venkatraman, Arun, Ziebart, Brian, Bagnell, J. Andrew
Imitation learning practitioners have often noted that conditioning policies on previous actions leads to a dramatic divergence between "held out" error and performance of the learner in situ. Interactive approaches can provably address this divergen
Externí odkaz:
http://arxiv.org/abs/2102.02872
Autor:
Venkatraman, Arun, Rhinehart, Nicholas, Sun, Wen, Pinto, Lerrel, Hebert, Martial, Boots, Byron, Kitani, Kris M., Bagnell, J. Andrew
Recurrent neural networks (RNNs) are a vital modeling technique that rely on internal states learned indirectly by optimization of a supervised, unsupervised, or reinforcement training loss. RNNs are used to model dynamic processes that are character
Externí odkaz:
http://arxiv.org/abs/1709.08520
Researchers have demonstrated state-of-the-art performance in sequential decision making problems (e.g., robotics control, sequential prediction) with deep neural network models. One often has access to near-optimal oracles that achieve good performa
Externí odkaz:
http://arxiv.org/abs/1703.01030
Boosting is a popular ensemble algorithm that generates more powerful learners by linearly combining base models from a simpler hypothesis class. In this work, we investigate the problem of adapting batch gradient boosting for minimizing convex loss
Externí odkaz:
http://arxiv.org/abs/1703.00377
Latent state space models are a fundamental and widely used tool for modeling dynamical systems. However, they are difficult to learn from data and learned models often lack performance guarantees on inference tasks such as filtering and prediction.
Externí odkaz:
http://arxiv.org/abs/1512.08836
Autor:
Muelling, Katharina, Venkatraman, Arun, Valois, Jean-Sebastien, Downey, John, Weiss, Jeffrey, Javdani, Shervin, Hebert, Martial, Schwartz, Andrew B., Collinger, Jennifer L., Bagnell, J. Andrew
Robot teleoperation systems face a common set of challenges including latency, low-dimensional user commands, and asymmetric control inputs. User control with Brain-Computer Interfaces (BCIs) exacerbates these problems through especially noisy and er
Externí odkaz:
http://arxiv.org/abs/1503.05451
Autor:
Rajendran, Karthik, Mahapatra, Durgamadhab, Venkatraman, Arun Venkatesh, Muthuswamy, Shanmugaprakash, Pugazhendhi, Arivalagan
Publikováno v:
In Renewable and Sustainable Energy Reviews May 2020 123
Autor:
Venkatraman, Arun
Publikováno v:
Dissertations.
Data driven approaches to modeling time-series are important in a variety of applications from market prediction in economics to the simulation of robotic systems. However, traditional supervised machine learning techniques designed for i.i.d. data o
Externí odkaz:
http://repository.cmu.edu/dissertations/1120
http://repository.cmu.edu/cgi/viewcontent.cgi?article=2159&context=dissertations
http://repository.cmu.edu/cgi/viewcontent.cgi?article=2159&context=dissertations
Autor:
Venkatraman, Arun
Data driven approaches to modeling time-series are important in a variety of applications from market prediction in economics to the simulation of robotic systems. However, traditional supervised machine learning techniques designed for i.i.d. data o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aeefbaa6f8cb0608491a663e93beea90
Data-driven approaches for learning dynamic models for Bayesian filtering often try to maximize the data likelihood given parametric forms for the transition and observation models. However, this objective is usually nonconvex in the parametrization
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0653fcf497dd9bc8cc614bcfe9f00e01