Media Summary: So essentially what I can do now is have a truly online TD We take a look at the example of Mountain Car to see how In this video, I demo a test I designed to help develop a RL algo
Reinforcement Learning Using Function Approximation - Detailed Analysis & Overview
So essentially what I can do now is have a truly online TD We take a look at the example of Mountain Car to see how In this video, I demo a test I designed to help develop a RL algo For more information about Stanford's Artificial Intelligence programs visit: To follow along Hado Van Hasselt, Research Scientist, discusses For more information about Stanford's Artificial Intelligence professional and graduate programs, visit:
This video is part of the Udacity course "