This is the code for "Introduction to AI for Video Games" by Siraj Raval on Youtube
This weeks coding challenge is to use the OpenAI Gym library to build a simple value iteration algorithm for any of the available environments. Use the learning resources I've listed in the video description for more help with this. I'll announce the top 2 entries next week, post your github link in the comment section of the video! I will personally review your code. Bonus points for good documentation, Good luck!
This is the code for this video on Youtube by Siraj Raval as part of the "AI for Video Games" course. In this first video I just introduce the idea of reinforcement learning and barely introduce the phrases "policy iteration" and "value iteration". I will go way more in depth next week.
- numpy
- OpenAI Gym
You can run both using python whatever_class_name.py
in terminal once dependencies are installed
The credits for this code go to malzantot. I've merely created a wrapper to get people started.