Fix constant epsilon bug and normalize readings to improve learning

harvitronix / reinforcement-learning-car

Using reinforcement learning to teach a car to avoid obstacles.

MIT License

488 stars 202 forks source link

Closed carriojazz closed 7 years ago

carriojazz commented 7 years ago

Epsilon will never decrease as this is currently a division of integers. Changing dividend type to float fixes the issue.

harvitronix commented 7 years ago

Thanks @carriojazz!