Improve Boids Reward

[PLAZMAMA]

Description

This PRs goal is to improve the reward calculation of the boids env and train a policy on it

Todo

• [x] Improve reward calculations

  • [x] margin factor
  • [x] separation factor
  • [x] cohesion factor
  • [x] alignment factor

• [x] Train policy on two factors

  • [x] Margin and seperation
  • [x] Cohesion and factor

• [x] Train policy successfully on all factors

[PLAZMAMA]

Hi @jsuarez5341, sorry for being out for the last 3 months, I got a new job and stuff.

However, I was able to improve the policy and solve Boids successfully with all of the rewards. All that's left is to do a sweep which I don't have the ability to do right now.

P.S. When I get situated in my new job(couple weeks hopefully) I'll come back to PufferLib and contribute in my free time. I look forward to working on cool stuff together again soon!