ConceptAI & ML
Bias/variance trade-off in reinforcement learning
Monte Carlo methods have high variance and zero bias, whereas Temporal Difference (TD) methods have lower variance but some bias.
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
2The lectures that define it or assume it, and the concepts next to it.