Shypd.aiThe largest open index of AI toolsMario-AI is an open-source project that trains an AI model to play Super Mario World using deep reinforcement learning. It utilizes raw pixel input and deep Q-learning with a spatial transformer to automatically play the first level.
Trending
About
Mario-AI is an open-source project available on GitHub that focuses on training an AI model to autonomously play the first level of Super Mario World. The system employs deep reinforcement learning, specifically deep Q-learning, and processes raw pixel input without relying on hand-engineered features. A key component is the integration of a Spatial Transformer, which helps the model make in-depth decisions based on the current game state. The methodology includes a replay memory for training, a unique reward function that accounts for movement and level progression, and an epsilon-greedy policy for action selection. The project details the model architecture, including branches for action history, screenshot history, and the last screenshot, and outlines the specific hardware and software requirements for installation and training, such as an NVIDIA GPU with CUDA and CUDNN, and Lua 5.1.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
