Version 1.0 of a machine learning Rocket League bot. Currently learning to play 1v1, thanks to RLGym. Objective is making a version that can take down pros!
This bot is trained with Deep Reinforcement Learning, a type of Machine Learning. The games are played at super speeds behind the scenes while the data is collected and learned from. Utilizing a personalised distributed learning system, these games are integrated.
Then, rewards are defined that the bot tries to achieve. Better Rocket League performance results from repeated reinforcement of behaviour that yields greater rewards over time.
