Learn to create an AI model that plays Doom using Python and reinforcement learning in this comprehensive video tutorial. Install and configure VizDoom, prepare it for reinforcement learning with OpenAI Gym, and build AI models using Stable Baselines 3. Explore training techniques for different Doom levels, implement curriculum learning and reward shaping to enhance performance. Follow along with step-by-step instructions, including setting up the environment, creating callbacks, training the model, and testing the agent. Witness AI results for various Doom levels, from basic to more complex scenarios like Defend Center and Deadly Corridor. Access provided code and resources to support your learning journey in gaming AI and reinforcement learning.
Build a Doom AI Model with Python - Gaming Reinforcement Learning Full Course
Overview
Syllabus
- Start
- Introduction
- Explainer
- CLIENT CONVERSATION 1
- Animation 1
- Tutorial Kickoff
- Getting VizDoom up and running
- CLIENT CONVERSATION 2
- Animation 2
- Creating an OpenAI Gym Environment
- CLIENT CONVERSATION 3
- Animation 3
- Setup Training Callback
- Train the RL model
- CLIENT CONVERSATION 4
- Testing the Agent
- BASIC LEVEL AI RESULTS
- CLIENT CONVERSATION 5
- Animation 4
- Changing Levels
- DEFEND CENTER LEVEL AI RESULTS
- CLIENT CONVERSATION 6
- Reward shaping
- Curriculum Learning
- DEADLY CORRIDOR LEVEL AI RESULTS
- FINAL CLIENT CALL
- Wrap up
Taught by
Nicholas Renotte
Related Courses
-
Reinforcement Learning for Gaming - Full Python Course
-
Python Reinforcement Learning using OpenAI Gymnasium – Full Course
-
Build a Mario AI Model with Python - Gaming Reinforcement Learning
-
Reinforcement Learning - Full Course Using Python
-
Deep Reinforcement Learning for Atari Games Python Tutorial - AI Plays Space Invaders
-
Build a Street Fighter AI Model with Python - Gaming Reinforcement Learning Full Course
