ConceptAI & ML
N-step returns
Returns accumulated over N steps instead of a single step to compute targets for Q-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.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
2Each in their own terms, from the easiest level.
Sergey Levine
An n-step backup method used in reinforcement learning to compute returns over multiple time steps before bootstrapping.David Silver
The return calculated from steps of actual rewards plus the discounted value estimate at state .
Lectures that assume it
1Connections
11The lectures that define it or assume it, and the concepts next to it.
Concepts7
- Discount factor
- Q-learning
- Bootstrapping
- Markov decision processes
- $\lambda$ return
- Averaging n-step returns