ConceptAI & ML
Off-policy learning
A learning paradigm where an agent learns the optimal policy while following a different, potentially suboptimal, behavior policy.
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.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
2Each in their own terms, from the easiest level.
Pieter Abbeel
Q-learning converges to the optimal policy even if the agent is acting sub-optimally while collecting data.David Silver
Learning about a target policy while following a different behavior policy.
Lectures that assume it
2Connections
11The lectures that define it or assume it, and the concepts next to it.