Parameter-Efficient Distributional RL via Normalizing Flows and a Geometry-Aware Cram\'er Surrogate

arXiv:2505.04310v2 Announce Type: replace Abstract: Distributional Reinforcement Learning (DistRL) improves upon expectation-based methods by modeling full return distributions, but standard approaches often remain far from parsimonious. Categorical methods (e.g., C51) rely on fixed supports where...