Best Paper Award at recent NeurIPS Workshop
Posted: 6th January 2023
The contribution titled "All’s Well That Ends Well: Avoiding Side Effects with Distance-Impact Penalties" has received a ‘best paper’ award at the recent NeurIPS Workshop on “Machine Learning Safety", which was held on 9 December 2022.
The contribution investigates how the use of bespoke distance-impact metrics in the context of Reinforcement Learning, allows to prevent side effects, whilst still permitting task completion.
The authors of this work are Charlie Griffin, Joar Max Viktor Skalse, Lewis Hammond and Alessandro Abate, all members of the Department of Computer Science, and of the Oxford Control & Verification group (OXCAV) - please visit the group’s webpage at: https://oxcav.web.ox.ac.uk/