Published On Feb 1, 2024
Intro to Makrov Decision Processes with a few first examples. The video we watched in the middle (cut from the actual recording) from Numberphile is at this link: • The Math of Being a Greedy Pig - Numb...
0:00 (Baby) Bellman Equation
1:45 Prizes
7:03 Markov Decision Processes
9:45 Examples of MDPs
12:39 Markov Property
16:00 Policy
18:35 Policy Evaluation
20:20 q-function for policy pi
23:30 Final Project Notes
30:18 Game of PIG (shows Numberphile Video)
30:36 Mathmatize Q1: PIG
32:48 Solutions to Mathmatize Q1
34:40 Graphical Representation
show more