Osbert Bastani

发表

Safe Reinforcement Learning via Online Shielding pdf

Osbert Bastani, O. Bastani, 2019, ArXiv.

A Composable Specification Language for Reinforcement Learning Tasks

Rajeev Alur, Osbert Bastani, Kishor Jothimurugan, 2020, NeurIPS.

Stanford's 2013 KBP System

Angel X. Chang, Christopher D. Manning, Gabor Angeli, 2013, TAC.

An Efficient Homomorphic Encryption Protocol for Multi-User Systems

I-Ling Yen, Osbert Bastani, Liangliang Xiao, 2012, IACR Cryptol. ePrint Arch..

Verifying Fairness Properties via Concentration pdf

Armando Solar-Lezama, Osbert Bastani, Xin Zhang, 2018, ArXiv.

An interactive approach to mobile app verification

Alexander Aiken, Osbert Bastani, Saswat Anand, 2015, MobileDeLi.

Program Synthesis Using Deduction-Guided Reinforcement Learning

Isil Dillig, Yu Feng, Osbert Bastani, 2020, CAV.

Abstract Value Iteration for Hierarchical Reinforcement Learning pdf

Rajeev Alur, Osbert Bastani, Kishor Jothimurugan, 2020, AISTATS.

Specification Inference Using Context-Free Language Reachability

Alexander Aiken, Osbert Bastani, Saswat Anand, 2015, POPL.

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

Osbert Bastani, O. Bastani, 2019, AISTATS.

Synthesizing Queries via Interactive Sketching pdf

Armando Solar-Lezama, Xin Zhang, Osbert Bastani, 2019, ArXiv.

Learning Neurosymbolic Generative Models via Program Synthesis pdf

Mayur Naik, Osbert Bastani, Halley Young, 2019, ICML.

Synthesizing program input grammars

Alexander Aiken, Rahul Sharma, Percy Liang, 2016, PLDI.

Polytopic Trees for Verification of Learning-Based Controllers

Osbert Bastani, Sadra Sadraddini, Shen Shen, 2019, NSV@CAV.

Ensuring Actionable Recourse via Adversarial Training pdf

Himabindu Lakkaraju, Osbert Bastani, Alexis Ross, 2020, ArXiv.

PolyDroid: Learning-Driven Specialization of Mobile Applications pdf

Mayur Naik, Osbert Bastani, Brian Heath, 2019, ArXiv.

Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shielding

Osbert Bastani, 2019 .

Active learning of points-to specifications

Alexander Aiken, Rahul Sharma, Percy Liang, 2017, PLDI.

Interpretability via Model Extraction pdf

Osbert Bastani, Hamsa Bastani, Carolyn Kim, 2017, ArXiv.

Minimizing GUI event traces

Alexander Aiken, Osbert Bastani, Saswat Anand, 2016, SIGSOFT FSE.

Eventually Sound Points-To Analysis with Specifications

Alexander Aiken, Rahul Sharma, Osbert Bastani, 2019, ECOOP.

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

Osbert Bastani, Wenbo Zhang, 2019, ArXiv.

Interactively verifying absence of explicit information flows in Android apps

Alexander Aiken, Osbert Bastani, Saswat Anand, 2015, OOPSLA.

Safe Planning via Model Predictive Shielding

Osbert Bastani, O. Bastani, 2019 .

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

Himabindu Lakkaraju, Osbert Bastani, Himabindu Lakkaraju, 2019, AIES.

Interpreting Blackbox Models via Model Extraction pdf

Osbert Bastani, Hamsa Bastani, Carolyn Kim, 2017, ArXiv.

Eventually Sound Points-To Analysis with Missing Code pdf

Alexander Aiken, Osbert Bastani, Saswat Anand, 2017, ArXiv.

Generating Programmatic Referring Expressions via Program Synthesis

Rishabh Singh, Aws Albarghouthi, Mayur Naik, 2020, ICML.

Synthesizing Programmatic Policies that Inductively Generalize

Armando Solar-Lezama, Osbert Bastani, Zenna Tavares, 2020, ICLR.

Verifiable Reinforcement Learning via Policy Extraction

Armando Solar-Lezama, Osbert Bastani, Yewen Pu, 2018, NeurIPS.

Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation pdf

Insup Lee, Sangdon Park, James Weimer, 2020, AISTATS.

Measuring Neural Net Robustness with Constraints

Antonio Criminisi, Leonidas Lampropoulos, Dimitrios Vytiniotis, 2016, NIPS.

PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction pdf

Insup Lee, Nikolai Matni, Sangdon Park, 2020, ICLR.

Relational verification using reinforcement learning

Isil Dillig, Osbert Bastani, Jiayi Wei, 2019, Proc. ACM Program. Lang..

Probabilistic verification of fairness properties via concentration

Armando Solar-Lezama, Osbert Bastani, Xin Zhang, 2018, Proc. ACM Program. Lang..

Automated Synthesis of Semantic Malware Signatures using Maximum Satisfiability pdf

Isil Dillig, Yu Feng, Ruben Martins, 2016, NDSS.

Randomization, Sums of Squares, and Faster Real Root Counting for Tetranomials and Beyond pdf

J. Maurice Rojas, Osbert Bastani, Christopher J. Hillar, 2011, ArXiv.

Neurosymbolic Transformers for Multi-Agent Communication pdf

Vijay Kumar, Armando Solar-Lezama, Martin C. Rinard, 2021, NeurIPS.

Program synthesis using conflict-driven learning

Isil Dillig, Yu Feng, Ruben Martins, 2017, PLDI.

Learning Interpretable Models with Causal Guarantees pdf

Osbert Bastani, Carolyn Kim, O. Bastani, 2019, ArXiv.

Fairness with Dynamics pdf

Ufuk Topcu, Min Wen, Osbert Bastani, 2019, ArXiv.

REINAM: reinforcement learning for input-grammar inference

Tao Xie, Dawn Xiaodong Song, Wei Yang, 2019, ESEC/SIGSOFT FSE.

Robust and Stable Black Box Explanations

Himabindu Lakkaraju, Nino Arsov, Osbert Bastani, 2020, ICML.

Diverse Sampling for Normalizing Flow Based Trajectory Forecasting pdf

Osbert Bastani, Dinesh Jayaraman, Jeevana Priya Inala, 2020, ArXiv.

PAC Confidence Predictions for Deep Neural Network Classifiers pdf

Insup Lee, Sangdon Park, Osbert Bastani, 2020, ArXiv.

Learning Safe Unlabeled Multi-Robot Planning with Motion Constraints

Vijay Kumar, Alejandro Ribeiro, Chi Zhang, 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics

Shuo Li, Osbert Bastani, 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning pdf

Osbert Bastani, Yecheng Jason Ma, Andrew Shen, 2021, AAAI.

Robust Generalization of Quadratic Neural Networks via Function Identification pdf

Osbert Bastani, Hamsa Bastani, Kan Xu, 2021, ArXiv.

Program Synthesis Guided Reinforcement Learning pdf

Martin Rinard, Armando Solar-Lezama, Osbert Bastani, 2021, ArXiv.

Safe Human-Interactive Control via Shielding pdf

Osbert Bastani, Jeevana Priya Inala, Yecheng Jason Ma, 2021, ArXiv.

Conservative Offline Distributional Reinforcement Learning pdf

Osbert Bastani, Dinesh Jayaraman, Yecheng Jason Ma, 2021, NeurIPS.

Abstract Value Iteration for Hierarchical Reinforcement Learning

Rajeev Alur, Osbert Bastani, Kishor Jothimurugan, 2021, AISTATS.

A Framework for Transforming Specifications in Reinforcement Learning pdf

Rajeev Alur, Osbert Bastani, Suguman Bansal, 2021, ArXiv.

Safe Reinforcement Learning via Statistical Model Predictive Shielding

Osbert Bastani, Shuo Li, Shuo Li, 2021, Robotics: Science and Systems.

SkyQuery: an aerial drone video sensing platform

Favyen Bastani, Osbert Bastani, Songtao He, 2021, Onward!.

Web question answering with neurosymbolic program synthesis

Isil Dillig, Osbert Bastani, Greg Durrett, 2021, PLDI.

Compositional Reinforcement Learning from Logical Specifications pdf

Rajeev Alur, Osbert Bastani, Suguman Bansal, 2021, NeurIPS.

Few-Shot Novel Concept Learning for Semantic Parsing

Dan Roth, Osbert Bastani, Soham Dan, 2021, EMNLP.

PAC Prediction Sets Under Covariate Shift pdf

Edgar Dobriban, Osbert Bastani, Insup Lee, 2021, ArXiv.

Safely Bridging Offline and Online Reinforcement Learning pdf

Osbert Bastani, Hamsa Bastani, Kan Xu, 2021, ArXiv.

Program Synthesis Guided Reinforcement Learning

Martin Rinard, Osbert Bastani, Yewen Pu, 2021, NeurIPS.

Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shielding

Osbert Bastani, O. Bastani, 2021, 2021 American Control Conference (ACC).

Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings

Osbert Bastani, Hamsa Bastani, Kan Xu, 2021, ICML.

Improving Human Decision-Making with Machine Learning pdf

Osbert Bastani, Hamsa Bastani, Wichinpong Park Sinchaisri, 2021, ArXiv.

Algorithms for Fairness in Sequential Decision Making

Ufuk Topcu, Osbert Bastani, Min Wen, 2019, AISTATS.

Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching pdf

Osbert Bastani, O. Bastani, 2021, ArXiv.

Synthesizing program input grammars

Alexander Aiken, Percy Liang, Osbert Bastani, 2016, ACM-SIGPLAN Symposium on Programming Language Design and Implementation.

Interpreting Predictive Models for Human-in-the-Loop Analytics

Osbert Bastani, Hamsa Bastani, 2018 .