AutoPilot

A prototypical project to experiment with reinforcement learning agents in unity. The training of the agents is handled locally, the game has embedded versions of the agents at different stages of training to illustrates their learning.

The project is based on Adam Kelly’s project along similar lines with a number of modifications in the training parameters. The two levels test of the agent’s speed and ability for precision flight. The snow level specifically challenges the agent’s depth perception using an invisible particle system to simulate fog.

Try it out to see how the agents fly and race against them!

Details of the project at : https://indrajeethaldar.com/AutoPilot.html

Note: The game, upon launching defaults to full-screen mode. Hit escape to pause and exit full-screen.