Teach AI to play Doom

In this video you'll learn how to:
- Install VizDoom for Python
- Prepare VizDoom for Reinforcement Learning with OpenAI Gym
- Build Reinforcement Learning AI models using Stable Baselines 3
- Train for different Doom levels
- Apply Curriculum Learning and Reward Shaping to improve results

Get the code: https://github.com/nicknochnack/DoomReinforcementLearning

Links:
VizDoom: http://vizdoom.cs.put.edu.pl/
OpenAI Gym: https://gym.openai.com/
PyTorch: https://pytorch.org/get-started/locally/
PPO Algorithm: https://stable-baselines3.readthedocs…

0:00 - Start
0:13 - Introduction
0:28 - Explainer
1:46 - CLIENT CONVERSATION 1
1:57 - Animation 1
2:09 - Tutorial Kickoff
3:01 - Getting VizDoom up and running
26:19 - CLIENT CONVERSATION 2
26:45 - Animation 2
27:16 - Creating an OpenAI Gym Environment
1:09:24 - CLIENT CONVERSATION 3
1:09:32 - Animation 3
1:13:32 - Setup Training Callback
1:22:21 - Train the RL model
1:45:28 - CLIENT CONVERSATION 4
1:45:41 - Testing the Agent
1:53:34 - BASIC LEVEL AI RESULTS
1:55:50 - CLIENT CONVERSATION 5
1:56:15 - Animation 4
1:56:30 - Changing Levels
2:11:16 - DEFEND CENTER LEVEL AI RESULTS
2:16:14 - CLIENT CONVERSATION 6
2:18:43 - Reward shaping
3:02:54 - Curriculum Learning
3:09:05 - DEADLY CORRIDOR LEVEL AI RESULTS
3:15:29 - FINAL CLIENT CALL
3:16:02 - Wrap up

Oh, and don't forget to connect with me!
LinkedIn: https://bit.ly/324Epgo
Facebook: https://bit.ly/3mB1sZD
GitHub: https://bit.ly/3mDJllD
Patreon: https://bit.ly/2OCn3UW
Join the Discussion on Discord: https://bit.ly/3dQiZsV

Happy coding!
Nick

P.s. Let me know how you go and drop a comment if you need a hand!
#ai #python