Combine cutting-edge reinforcement learning techniques with deep learning architectures. Use Q-networks and experience replay to train agents capable of navigating and adapting to real-time environments.
Overview
Syllabus
- Study Plan
- This lesson covers the study plan and prerequisites for this course.
- Deep Q-Networks
- Extend value-based reinforcement learning methods to complex problems using deep neural networks.
- Project: Navigation
- Train an agent to navigate a large world and collect yellow bananas, while avoiding blue bananas.
Taught by
Dana Sheahen, Arpan Chakraborty and Kelvin Lwin
