Parameter-Efficient Distributional RL via Normalizing Flows and a Geometry-Aware Cram\'er Surrogate
📰 ArXiv cs.AI
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 parameter counts scale linearly with resolution, while quantile methods approximate distributions as discrete mixtures whose piecewise-constant densities can be wasteful when modeling complex multi-mod
Full Article
Title: Parameter-Efficient Distributional RL via Normalizing Flows and a Geometry-Aware Cram\'er Surrogate
Abstract:
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 parameter counts scale linearly with resolution, while quantile methods approximate distributions as discrete mixtures whose piecewise-constant densities can be wasteful when modeling complex multi-mod
Abstract:
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 parameter counts scale linearly with resolution, while quantile methods approximate distributions as discrete mixtures whose piecewise-constant densities can be wasteful when modeling complex multi-mod
DeepCamp AI