Premium Content

DDPG and TD3

Deterministic policy gradients for continuous control

This chapter requires a subscription to access.

What you'll unlock:

  • 1. The Deterministic Policy Gradient
  • 2. DDPG
  • 3. TD3: Twin Critics and Delayed Updates
  • 4. Target Policy Smoothing
  • 5. TD3 on MuJoCo: Hopper, HalfCheetah, Ant
Subscribe to Unlock

Already have an account? Sign in