Premium ContentPlanning and Learning with Dyna
Unifying model-free and model-based
This chapter requires a subscription to access.
What you'll unlock:
- 1. Tabular Dyna-Q
- 2. Dyna-Q+ for Non-Stationary Worlds
- 3. Prioritized Sweeping
- 4. Trajectory Sampling vs Uniform Updates
Subscribe to UnlockAlready have an account? Sign in