3 papers
cs.LG2025
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…
cs.LG2024
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…
cs.LG2024
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…