2nd attempt (Renforcement Learning this time)
This is an untrained RL agent that is meant to look at the enamy, there is some signs that it would converge on a solution eventually but i dont have enough time to train it.
Here is the video report i do some talking about about 12 mins then its just the AI running in the env https://1drv.ms/v/s!AhKDfKsG6_tQn6QBIILY4fL4RkX1xQ?e=QKm7QM