mario-ai and reinforcement-learning-game
About mario-ai
aleju/mario-ai
Playing Mario with Deep Reinforcement Learning
This project offers a way to train a digital agent to play the classic video game Super Mario World using only the game's visuals as input. The agent learns to press the right buttons by observing the screen, trying different actions, and remembering what leads to success or failure. This tool is for researchers or enthusiasts in artificial intelligence who want to experiment with creating smart agents for games.
About reinforcement-learning-game
slrbl/reinforcement-learning-game
A random environment reinforcement learning-powered Mario game
This project lets you watch a computer program learn to play a Mario-like game on its own. It takes a game environment where the layout changes randomly and shows you how an AI agent, starting with no knowledge, improves its gameplay over time. Anyone curious about how artificial intelligence learns through trial and error, like a student or an AI enthusiast, would find this engaging.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work