Reinforcement Learning Deep Q-Learning PyTorch Tutorial [Part 4]: Double Q-Learning (DDQN)

👉Check out https://www.eteria.ai
Eteria AI is democratizing access to advanced AI models.

Learn how to improve our Deep Q-Learning implementation from the previous videos using Double Q-Learning.

In this video, I explain the difference between Double Q-Learning (DDQN) and Vanilla Q-Learning, thoroughly explaining the key equation in the paper. Then I demonstrate how to code DDQN in PyTorch, and compare training graphs between vanilla and double q-learning on Breakout and Space Invaders atari gym environments.

Download the starter code: https://www.brthor.com/yt/?v=QeRQLhULF90

Contents:
0:00 - Intro
0:23 - Double Q-Learning Equation
1:20 - Coding DDQN
4:24 - Training Results
6:53 - Space Invaders Demo

Видео Reinforcement Learning Deep Q-Learning PyTorch Tutorial [Part 4]: Double Q-Learning (DDQN) канала brthor

dqn ddqn double q-learning deep q-learning q-learning reinforcement learning pytorch python

Комментарии отсутствуют

Информация о видео

30 января 2021 г. 1:00:12

00:07:26

brthor

Теги

Правообладателям

Жалоба на материал Недопустимый материал Нарушение авторских прав

Комментарии

Другие видео канала

Reinforcement Learning Deep Q-Learning PyTorch Tutorial [Part 4]: Double Q-Learning (DDQN)

Reinforcement Learning For Classification?

KiCad (5.1): Create a Footprint

Coding Deep Q-Learning in PyTorch - Reinforcement Learning DQN Code Tutorial Series p.1

KiCad (5.1): Install on Ubuntu 18.04 & Add DigiKey Libraries

Sharing the Raspberry Pi's WiFi over the Ethernet Port

Deep Q Network Learns Game Breaking Atari Strategy - DQN Reinforcement Learning Code Tutorial p.3

Train Deep Q-Learning on Atari in PyTorch - Reinforcement Learning DQN Code Tutorial Series p.2

Learn Minecraft Modding [1]: Setup Minecraft Forge (1.12.2) in IntelliJ IDEA in 5 minutes