no code implementations • 9 Oct 2023 • Kaustubh Sridhar, Souradeep Dutta, Dinesh Jayaraman, James Weimer, Insup Lee
Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations.
1 code implementation • 2 Dec 2022 • Kaustubh Sridhar, Souradeep Dutta, James Weimer, Insup Lee
Next, using these memories we partition the state space into disjoint subsets and compute bounds that should be respected by the neural network in each subset.
no code implementations • 2 Dec 2022 • Kaustubh Sridhar, Vikramank Singh, Balakrishnan Narayanaswamy, Abishek Sankararaman
PnC jointly trains a prediction model and a terminal Q function that approximates cost-to-go over a long horizon, by back-propagating the cost of decisions through the optimization problem \emph{and from the future}.
1 code implementation • 24 Jul 2022 • Ramneet Kaur, Kaustubh Sridhar, Sangdon Park, Susmit Jha, Anirban Roy, Oleg Sokolsky, Insup Lee
Machine learning models are prone to making incorrect predictions on inputs that are far from the training distribution.
1 code implementation • 13 Jun 2022 • Kaustubh Sridhar, Souradeep Dutta, Ramneet Kaur, James Weimer, Oleg Sokolsky, Insup Lee
Algorithm design of AT and its variants are focused on training models at a specified perturbation strength $\epsilon$ and only using the feedback from the performance of that $\epsilon$-robust model to improve the algorithm.
1 code implementation • 25 Feb 2022 • Souradeep Dutta, Kaustubh Sridhar, Osbert Bastani, Edgar Dobriban, James Weimer, Insup Lee, Julia Parish-Morris
We formulate expert intervention as allowing the agent to execute option templates before learning an implementation.
1 code implementation • 3 Jun 2021 • Kaustubh Sridhar, Oleg Sokolsky, Insup Lee, James Weimer
Improving adversarial robustness of neural networks remains a major challenge.
no code implementations • 23 Feb 2020 • Yiannis Kantaros, Taylor Carpenter, Kaustubh Sridhar, Yahan Yang, Insup Lee, James Weimer
To highlight this, we demonstrate the efficiency of the proposed detector on ImageNet, a task that is computationally challenging for the majority of relevant defenses, and on physically attacked traffic signs that may be encountered in real-time autonomy applications.