ML: Distributional rl

Directional Almost-Dominance OT Loss

Add a directional optimal-transport penalty that discourages samples from a model distribution P from exceeding samples from a reference distribution Q in task-relevant coordinates, while allowing a calibrated amount of violation controlled by γ. Unlike symmetric Wasserstein matching, the loss distinguishes harmful upward or downward deviations and can encode that one predictive or reward distribution should dominate another.