Back
Park my car: training a reinforcement learning agent to park a car in a parking lot, in a simulated environment in Godot.
The Bear: A banana eating bear in a random simulated environment with a few sensors needs to learn how to navigate around to stay alive. Still in Godot.
The hexapod: training several iterations of a 3D hexapod robot to walk in a simulated environment in Unity.
Adventures in Reinforcement Learning
completedA couple of projects around reinforcement learning in simulated environments
Notes
I saw the DeepMind documentary and read What is Intelligence from Blaise Aguera y Arcas, and fell into a consuming rabbit hole about reinforcement learning.



The three projects are using PPO.