ConceptAI & ML
Action prior handling
Non-uniform action priors can be folded directly into the reward function, allowing the use of algorithms assuming a uniform action prior without loss of generality.
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.
Action prior1
Lecturers
1Connections
1The lectures that define it or assume it, and the concepts next to it.