2019 Publications

 

1. Tyler Westenbroek, David Fridovich-Keil, Eric Mazumdar, Shreyas Arora, Valmik Prabhu, S. Shankar Sastry, and Claire J. Tomlin. Feedback Linearization for Unknown Systems via Reinforcement Learning. arXiv preprint arXiv:1910.13272 (2019). [PDF]

2. K. Nar, S. S. Sastry. Persistency of excitation for robustness of neural networks. arXiv: 1911.01043 cs.LG, (2019). [PDF]

3. Tyler Westenbroek, Xiaobin Xiong, Aaron Ames and Shankar Sastry. Optimal Control for Piecewise-Smooth Systems Via Singular Perturbation. Conference on Decision and Control, (2019). [PDF]

4. J. F. Fisac, E. Bronstein, E. Stefansson, D. Sadigh, S. S. Sastry, and A. D. Dragan. Hierarchical Game- Theoretic Planning for Autonomous Vehicles. International Conference on Robotics and Automation (ICRA), 2019.[PDF]

5. DorsaSadigh, S.ShankarSastry, SanjitA.Seshia. Verifying Robustness ofHuman-Aware Autonomous Cars. ELSEVIER SCIENCE BV. 2019: 13138. [PDF]

6. Eric Mazumdar, Lillian J. Ratliff, Shankar Sastry, Michael I. Jordan. Policy Gradient in Linear Quadratic Dynamic Games Has No Convergence Guarantees. Smooth Games Optimization and Machine Learning Workshop: Bridging Game Theory and Deep Learning, NeuRIPS, 2019.

7. Tyler Westenbroek, Roy Dong, Lillian J. Ratliff, and S. Shankar Sastry. Competitive Settings Statistical Estimation with Strategic Data Sources. In IEEE Transactions on Automatic Control, 2019. [PDF]

8. Kamil Nar, Orhan Ocal, S. Shankar Sastry, Kannan Ramchandran. Cross-Entropy Loss and Low-Rank Features Have Responsibilityfor Adversarial Examples. arxiv1901.08360, 2019. [PDF]

9. Eric Mazumdar, Michael I. Jordan, S. Shankar Sastry. On Finding Local Nash Equilibria (and Only Local Nash Equilibria)

in Zero-Sum Continuous Games. arxiv1901.00838, 2019. [PDF]