Premium Content

Learned World Models

Learning to predict and plan

This chapter requires a subscription to access.

What you'll unlock:

  • 1. Why Model-Based RL?
  • 2. PETS: Probabilistic Ensembles with Trajectory Sampling
  • 3. MBPO: Model-Based Policy Optimization
  • 4. World Models (Ha and Schmidhuber)
  • 5. Dreamer V1 and V2
  • 6. DreamerV3: Mastering Diverse Domains
Subscribe to Unlock

Already have an account? Sign in