159 citations · 798 across the 116 of their papers we have counts for
15 papers · 1 filter
Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning
Yecheng Jason Ma, Andrew Shen, Osbert Bastani +1
Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in addition to maximizing a reward objective. Model-based RL algorithms hold promise for reduci…
A Framework for Transforming Specifications in Reinforcement Learning
Rajeev Alur, Suguman Bansal, Osbert Bastani +1
Reactive synthesis algorithms allow automatic construction of policies to control an environment modeled as a Markov Decision Process (MDP) that are optimal with respect to high-le…
Safe Human-Interactive Control via Shielding
Jeevana Priya Inala, Yecheng Jason Ma, Osbert Bastani +2
Ensuring safety for human-interactive robotics is important due to the potential for human injury. The key challenge is defining safety in a way that accounts for the complex range…
Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching
Osbert Bastani
We study the problem of synthesizing programs that include machine learning components such as deep neural networks (DNNs). We focus on statistical properties, which are properties…
Uniformly Conservative Exploration in Reinforcement Learning
Wanqiao Xu, Jason Yecheng Ma, Kan Xu +2
A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes. We propose a natural constraint on exploration -…
Robust Generalization of Quadratic Neural Networks via Function Identification
Kan Xu, Hamsa Bastani, Osbert Bastani
A key challenge facing deep learning is that neural networks are often not robust to shifts in the underlying data distribution. We study this problem from the perspective of the s…