AI Learns to Play MORTAL KOMBAT

Опубликовано: 17 Апрель 2026
на канале: Will Kwan
147,806
5k

So I trained a bot to beat up the in-game bots in Mortal Kombat II.

This was my first time automating a game with machine learning and my first reinforcement learning project, so I learned a lot! I used the PPO2 algorithm that OpenAI used to train their Dota AI.

Source code: https://github.com/wkwan/mkii-subzero...

Helpful videos:
‪@LucasThompson‬ (his channel is the best resource I found for Gym Retro) - An AI Defeats Street Fighter 2!
   • An AI Defeats Street Fighter 2!  

​‪@ArxivInsights‬ (only has a few videos but he's great at explaining papers without dumbing it down too much) - Policy Gradient methods and Proximal Policy Optimization (PPO): diving into Deep RL!
   • An introduction to Policy Gradient methods...  

‪@googledeepmind‬RL Course by David Silver
   • RL Course by David Silver - Lecture 1: Int...  

Some fun game AI's I was inspired by:
‪@CodeBullet‬AI learns to play Google Chrome Dinosaur Game || Can you beat it??
   • AI learns to play Google Chrome Dinosaur G...  

‪@SethBling‬MarI/O - Machine Learning for Video Games
   • MarI/O - Machine Learning for Video Games  

‪@OpenAI‬Dendi vs. OpenAI at The International 2017
   • Dendi vs. OpenAI at The International 2017