Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Osbert Bastani

Program Synthesis Guided Reinforcement Learning


Feb 22, 2021
Yichen Yang, Jeevana Priya Inala, Osbert Bastani, Yewen Pu, Armando Solar-Lezama, Martin Rinard


  Access Paper or Ask Questions

Neurosymbolic Transformers for Multi-Agent Communication


Jan 05, 2021
Jeevana Priya Inala, Yichen Yang, James Paulos, Yewen Pu, Osbert Bastani, Vijay Kumar, Martin Rinard, Armando Solar-Lezama


  Access Paper or Ask Questions

Diverse Sampling for Normalizing Flow Based Trajectory Forecasting


Nov 30, 2020
Yecheng Jason Ma, Jeevana Priya Inala, Dinesh Jayaraman, Osbert Bastani

* Technical report, 18 pages 

  Access Paper or Ask Questions

Robust and Stable Black Box Explanations


Nov 12, 2020
Himabindu Lakkaraju, Nino Arsov, Osbert Bastani


  Access Paper or Ask Questions

Ensuring Actionable Recourse via Adversarial Training


Nov 12, 2020
Alexis Ross, Himabindu Lakkaraju, Osbert Bastani


  Access Paper or Ask Questions

PAC Confidence Predictions for Deep Neural Network Classifiers


Nov 09, 2020
Sangdon Park, Shuo Li, Osbert Bastani, Insup Lee


  Access Paper or Ask Questions

Abstract Value Iteration for Hierarchical Reinforcement Learning


Oct 29, 2020
Kishor Jothimurugan, Osbert Bastani, Rajeev Alur


  Access Paper or Ask Questions

A Composable Specification Language for Reinforcement Learning Tasks


Aug 21, 2020
Kishor Jothimurugan, Rajeev Alur, Osbert Bastani

* In Advances in Neural Information Processing Systems, pp. 13041-13051. 2019 

  Access Paper or Ask Questions

Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation


Feb 29, 2020
Sangdon Park, Osbert Bastani, James Weimer, Insup Lee

* Accepted to AISTATS 2020 

  Access Paper or Ask Questions

PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction


Feb 15, 2020
Sangdon Park, Osbert Bastani, Nikolai Matni, Insup Lee

* Accepted to ICLR 2020 

  Access Paper or Ask Questions

"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations


Nov 15, 2019
Himabindu Lakkaraju, Osbert Bastani


  Access Paper or Ask Questions

MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding


Oct 25, 2019
Wenbo Zhang, Osbert Bastani


  Access Paper or Ask Questions

Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics


Oct 24, 2019
Shuo Li, Osbert Bastani

* 8 pages, 5 figures 

  Access Paper or Ask Questions

Learning Safe Unlabeled Multi-Robot Planning with Motion Constraints


Jul 11, 2019
Arbaaz Khan, Chi Zhang, Shuo Li, Jiayue Wu, Brent Schlotfeldt, Sarah Y. Tang, Alejandro Ribeiro, Osbert Bastani, Vijay Kumar


  Access Paper or Ask Questions

Safe Reinforcement Learning via Online Shielding


May 25, 2019
Osbert Bastani


  Access Paper or Ask Questions

Learning Interpretable Models with Causal Guarantees


Jan 24, 2019
Carolyn Kim, Osbert Bastani


  Access Paper or Ask Questions

Fairness with Dynamics


Jan 24, 2019
Min Wen, Osbert Bastani, Ufuk Topcu


  Access Paper or Ask Questions

Learning Neurosymbolic Generative Models via Program Synthesis


Jan 24, 2019
Halley Young, Osbert Bastani, Mayur Naik


  Access Paper or Ask Questions

Sample Complexity of Estimating the Policy Gradient for Nearly Deterministic Dynamical Systems


Jan 24, 2019
Osbert Bastani


  Access Paper or Ask Questions

Verifying Fairness Properties via Concentration


Dec 02, 2018
Osbert Bastani, Xin Zhang, Armando Solar-Lezama


  Access Paper or Ask Questions

Interpreting Blackbox Models via Model Extraction


May 22, 2018
Osbert Bastani, Carolyn Kim, Hamsa Bastani


  Access Paper or Ask Questions

Verifiable Reinforcement Learning via Policy Extraction


May 22, 2018
Osbert Bastani, Yewen Pu, Armando Solar-Lezama


  Access Paper or Ask Questions

Interpretability via Model Extraction


Mar 13, 2018
Osbert Bastani, Carolyn Kim, Hamsa Bastani

* Presented as a poster at the 2017 Workshop on Fairness, Accountability, and Transparency in Machine Learning (FAT/ML 2017) 

  Access Paper or Ask Questions

Measuring Neural Net Robustness with Constraints


Jun 16, 2017
Osbert Bastani, Yani Ioannou, Leonidas Lampropoulos, Dimitrios Vytiniotis, Aditya Nori, Antonio Criminisi


  Access Paper or Ask Questions

Zero-Shot Learning Through Cross-Modal Transfer


Mar 20, 2013
Richard Socher, Milind Ganjoo, Hamsa Sridhar, Osbert Bastani, Christopher D. Manning, Andrew Y. Ng


  Access Paper or Ask Questions