← Back to Data Science

All Topics

Advertisement

Learn/Data Science/Machine Learning

Actor-Critic Methods

Topic: RL

Advertisement

Combine Value and Policy

Actor-critic architecture.

A2C/A3C

Asynchronous advantage actor-critic.

PPO

Proximal policy optimization. Clipped objective.

SAC

Soft actor-critic. Entropy regularization.

Key Takeaways

  1. Actor-critic combines value and policy
  2. PPO uses clipped objective
  3. SAC maximizes entropy

Advertisement

Advertisement

Need More Practice?

Get personalized data science help from ChatWhole's AI-powered platform.

Get Expert Help →