Premium ContentActor-Critic Methods
Combining policy and value
This chapter requires a subscription to access.
What you'll unlock:
- 1. From REINFORCE to Actor-Critic
- 2. Advantage Estimation
- 3. A2C: Synchronous Advantage Actor-Critic
- 4. A3C: Asynchronous Actor-Critic
- 5. Generalized Advantage Estimation (GAE)
Subscribe to UnlockAlready have an account? Sign in