Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Trust Region & Proximal Policy Optimization

Pascal Poupart via YouTube

Start learning Write review
Coursera Ad

AI, Data Science & Cloud Certificates from Google, IBM & Meta

Learn More → Corporate Finance Institute Ad

Finance Certifications Goldman Sachs and Amazon Teams Trust

Learn More →

Overview

Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This lecture explains trust-region and proximal policy optimization methods for reinforcement learning. It covers policy gradients, KL divergence, constrained optimization, TRPO and PPO algorithms, and empirical results.

Syllabus

Gradient policy optimization
Recall Policy Gradient
Trust region method
Trust region for policies
Kullback-Leibler Divergence
Reformulation
Derivation (continued)
Trust Region Policy Optimization (TRPO) TRPOO Initialize sa to anything Loop forever (for each episode)
Constrained Optimization
Simpler Objective
Proximal Policy Optimization (PPO)
Empirical Results
Illustration

Taught by

Pascal Poupart

Reviews

Start your review of Trust Region & Proximal Policy Optimization

Start learning

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.