Deep Reinforcement Learning with Proximal Policy Optimization (PPO) with Code example!

Опубликовано: 04 Февраль 2026
на канале: Luke Ditria
7,850
177

VIDEO TIMESTAMPS
00:00 Intro
01:30 Why PPO?
02:20 Actor Critic Issues
05:20 Improvements to make
06:50 RL Training Procedure
08:00 TRPO
14:50 GAE
21:10 PPO
31:15 PPO Implementation


In this series we're going to look into how we can apply deep learning to Reinforcement Learning!
In this video we discuss the concepts around PPO and how we can use them to create an RL implementation that work with a complicated environment! Finally we'll see how we can train a reinforcement learning agent to play a game!

Code and slides here! (section 11 RL)
https://github.com/LukeDitria/pytorch...

Discord Server:
  / discord  

Donations
https://www.buymeacoffee.com/lukeditria