This is a series of companion videos to Sutton & Barto's textbook on reinforcement learning used by some of the best universities as standard course text - including Stanford, UCL, Carnegie Mellon
Download Book for free: incompleteideas...
Buy on Amazon: www.amazon.com...
Github Code Repository: github.com/Sha...
This second video covers the first few sections of chapter one.
00:00:00 Video intro
00:00:35 Overview of key code components - Loop through entire state space
00:03:56 Overview of key code components - State Class - hash, numpy array, next state method
00:06:55 Overview of key code components - Player Class - step size and epsilon-greedy configuration, backup algorithm, value table, choosing actions
00:14:45 Overview of key code components - Judger Class
00:15:30 Training function - save value table to permanent storage - binary file
00:16:54 Compete function - epsilon = 0 - greedy play, load policy
00:17:44 Python code demo and detailed explanation