FlapPyBird 1: Introduction to using REINFORCE to play FlapPyBird

We're going to use policy gradients to learn to play FlapPyBird. In this video, we go over some of the new concepts we will encounter compared to our previous RL projects.
FlapPyBird is a Python implementation of the Flappy Bird game. We’re going to use PyTorch to create a neural network that will learn to play, on its own, using REINFORCE algorithm. This is the first part of a playlist, • FlapPyBird RL
Contents:
00:00 - Welcome
01:18 - Movement
02:49 - Resolution
03:20 - Stacking previous frames
04:02 - Muscle memory
04:49 - Outro

[@navins2246]

You have amazing content