Search Results for author: Stephen Scott

Found 4 papers, 1 papers with code

BEVERS: A General, Simple, and Performant Framework for Automatic Fact Verification

no code implementations29 Mar 2023 Mitchell DeHaven, Stephen Scott

We also apply this pipeline to another fact verification dataset, Scifact, and achieve the highest label accuracy among all systems on that dataset as well.

Fact Verification Retrieval +1

Formal Language Constraints for Markov Decision Processes

1 code implementation2 Oct 2019 Eleanor Quint, Dong Xu, Samuel Flint, Stephen Scott, Matthew Dwyer

In order to satisfy safety conditions, an agent may be constrained from acting freely.

Atari Games

Constraining Action Sequences with Formal Languages for Deep Reinforcement Learning

no code implementations27 Sep 2018 Dong Xu, Eleanor Quint, Zeynep Hakguder, Haluk Dogan, Stephen Scott, Matthew Dwyer

We study the problem of deep reinforcement learning where the agent's action sequences are constrained, e. g., prohibition of dithering or overactuating action sequences that might damage a robot, drone, or other physical device.

Atari Games reinforcement-learning +1

Interpretable Classification via Supervised Variational Autoencoders and Differentiable Decision Trees

no code implementations ICLR 2018 Eleanor Quint, Garrett Wirka, Jacob Williams, Stephen Scott, N. V. Vinodchandran

As deep learning-based classifiers are increasingly adopted in real-world applications, the importance of understanding how a particular label is chosen grows.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.