3 citations · 5 across the 5 of their papers we have counts for
5 papers
Criticality and Safety Margins for Reinforcement Learning
Alexander Grushin, Walt Woods, Alvaro Velasquez +1
State of the art reinforcement learning methods sometimes encounter unsafe situations. Identifying when these situations occur is of interest both for post-hoc analysis and during…
Combining AI Control Systems and Human Decision Support via Robustness and Criticality
Walt Woods, Alexander Grushin, Simon Khan +1
AI-enabled capabilities are reaching the requisite level of maturity to be deployed in the real world, yet do not always make correct or safe decisions. One way of addressing these…
Training Neural Networks with Internal State, Unconstrained Connectivity, and Discrete Activations
Alexander Grushin
Today's most powerful machine learning approaches are typically designed to train stateless architectures with predefined layers and differentiable activation functions. While thes…
Safety Margins for Reinforcement Learning
Alexander Grushin, Walt Woods, Alvaro Velasquez +1
Any autonomous controller will be unsafe in some situations. The ability to quantitatively identify when these unsafe situations are about to occur is crucial for drawing timely hu…
Anomaly Detection with Neural Parsers That Never Reject
Alexander Grushin, Walt Woods
Reinforcement learning has recently shown promise as a technique for training an artificial neural network to parse sentences in some unknown format, through a body of work known a…