Add mappo navigation learning path

[spsagar13]

Before submitting a pull request for a new Learning Path, please review Create a Learning Path

• I have reviewed Create a Learning Path

Please do not include any confidential information in your contribution. This includes confidential microarchitecture details and unannounced product information.

• I have checked my contribution for confidential information

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of the Creative Commons Attribution 4.0 International License.

Summary

Adds a new Learning Path for training Multi-Agent Reinforcement Learning navigation policies with MAPPO, BenchMARL, and VMAS on Arm cloud instances.

The Learning Path covers:

• Arm cloud environment setup
• MAPPO training with configurable agent and environment counts
• Training checkpoint validation
• Deployment of trained checkpoints to a visualization GUI
• Export and validation of an actor-only model for downstream inference

The steps have been tested end-to-end on an Arm cloud instance, and the Learning Path builds successfully with Hugo.