[RLlib] Add PyFlyte Example Using Gymnasium and Ray Tune

[peterghaddad]

Description

Add a PPO RLlib + Ray Tune that trains an agent on a PyFlyt environment.

Additionally, this example will showcase how to register an environment in gymnasium while leveraging their wrappers to adjust the reward function to maximize learning potential.

Use case

Showcase how to:

• register a gymnasium environment for use with Ray Tune and RLlib.
• wrap and adjust environment functions using Gymnasium wrappers as a potential solution instead of adjusting hyperparameters from the start.
• train an agent in a difficult observation space.