10.9k citations
- University of PennsylvaniaUS377 papers
- University of MichiganUS93 papers
- University of ChicagoUS91 papers
- University College LondonGB90 papers
- University of OxfordGB90 papers
- University of Illinois Urbana-ChampaignUS86 papers
- Lawrence Berkeley National LaboratoryUS85 papers
- University of Wisconsin–MadisonUS84 papers
- The Ohio State UniversityUS82 papers
- Yale UniversityUS82 papers
- Argonne National LaboratoryUS80 papers
- Duke UniversityUS80 papers
9 papers · 2 filters
Robust and Stable Black Box Explanations
Himabindu Lakkaraju, Nino Arsov, Osbert Bastani
As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the…
Abstract Value Iteration for Hierarchical Reinforcement Learning
Kishor Jothimurugan, Osbert Bastani, Rajeev Alur
We propose a novel hierarchical reinforcement learning framework for control with continuous state and action spaces. In our framework, the user specifies subgoal regions which are…
In Search of Robust Measures of Generalization
Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal +5
One of the principal scientific challenges in deep learning is explaining generalization, i.e., why the particular way the community now trains networks to achieve small training e…
Moment Multicalibration for Uncertainty Estimation
Christopher Jung, Changhwa Lee, Mallesh M. Pai +2
We show how to achieve the notion of "multicalibration" from Hébert-Johnson et al. [2018] not just for means, but also for variances and other higher moments. Informally, it means…
A Composable Specification Language for Reinforcement Learning Tasks
Kishor Jothimurugan, Rajeev Alur, Osbert Bastani
Reinforcement learning is a promising approach for learning control policies for robot tasks. However, specifying complex tasks (e.g., with multiple objectives and safety constrain…
Planning to Explore via Self-Supervised World Models
Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis +3
Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-…