ConceptAI & ML
Exploitability of Learned policies (NashGap)
A metric measuring the maximal regret among agents when one deviates from the expert policy in multi-agent imitation learning.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Lecturers
1Connections
3The lectures that define it or assume it, and the concepts next to it.