ML-Agents: The Mayan Adventure
Published 3 days ago
Train an agent to get the golden statue in this dangerous environment.
I’m launching the Mayan Adventure. An open-source deep reinforcement learning environment on Unity ML-Agents.
In this environment, you train your agent (Indie) to find the golden statue in this dangerous environment full of traps. Your agent will learn to cross the bridge, change its physics to cross the fire etc.
I designed the project to be as modular as possible, it means that you will be able to create new levels and new obstacles. I’m currently working on two new levels: a rotating bridge and a rolling boulder level.
You can read the article here.
You can access the github project repo here.
Thomas Simonini
Deep Reinforcement Learning Engineer - Other