AI, Data Science & Cloud Certificates from Google, IBM & Meta
Learn Generative AI, Prompt Engineering, and LLMs for Free
Overview
Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This lecture surveys deep reinforcement learning methods that use neural networks, including deep policy networks, policy gradient optimization, deep Q-learning, and actor-critic networks. It emphasizes how these approaches represent policies or value functions and optimize them in high-dimensional state spaces.
Syllabus
Intro
REINFORCEMENT LEARNING
DEEP POLICY NETWORK
POLICY GRADIENT OPTIMIZATION
DEEP Q-LEARNING
ADVANTAGE ACTOR-CRITIC NETWORK
Taught by
Steve Brunton