Opening Exploration of advanced topics in deep reinforcement learning
Exploration of advanced topics in deep reinforcement learning
- Length
- 16 min
- Level
- Graduate
- Recorded
- UC Berkeley2020
Chapter 1 of 3: State and action dependent baselines
UC Berkeley CS 285 covers bias and variance in policy gradient estimation in this graduate session. Levine contrasts state- and action-dependent baselines, shows how truncating returns trades bias against variance, and derives generalized advantage estimation.

Your comment is kept while you sign up.Sign in
Derives generalized advantage estimation as a weighted average of all n-step return estimators.
UC Berkeley CS 285 covers bias and variance in policy gradient estimation in this graduate session. Levine contrasts state- and action-dependent baselines, shows how truncating returns trades bias against variance, and derives generalized advantage estimation.
Q-Prop
High-Dimensional Continuous Control Using Generalized Advantage Estimation
This lecture
Lecture 16 of 73 of Deep Reinforcement Learning.
Choose a node to see how it connects to this lecture. What comes before is on the leftat the top. What comes after is on the rightat the bottom. The ring is what it teaches. People and places are above. Other lectures and books are below.
Press a chosen node again to open it.