[skyrl-train] Integrate Ray Core RDT for weight syncing

[erictang000]

Integrate RDT as a new weight syncing backend: https://docs.ray.io/en/latest/ray-core/direct-transport.html

Additional milestone once RDT is integrated is to use it to dynamically add inference engines to the rollout pool (failure handling, autoscaling, etc.) since we will be able to initiate weight sync without forming a new NCCL group.