[FEATURE]: MAD4PG Quantile Regression

[DriesSmit]

Please describe the purpose of the feature. Is it related to a problem?

To improve MAD4PG's performance while also reducing its hyperparameters which reduces possible user error.

Describe the solution you'd like

Implement Quantile Regression for MAD4PG instead of fixing the distributional value head's range manually. Paper: https://arxiv.org/pdf/1710.10044.pdf

Describe alternatives you've considered

A clear and concise description of any alternative solutions or features you've considered.

How do we know when implementation of this feature is complete?

Checklist:

• [ ] MAD4PG uses Quantile Regression in its value function.
• [ ] MAD4PG outperforms the previous version in all environments.

[DriesSmit]

Closing all TF issues as we are depreciating our TF systems.