
TM
Thomas Mousseau, Tyler Kastner, Davide Baldelli, Amir-massoud Farahmand
· 1 min read
ResearcharXiv cs.LG
{\phi}TD: Distributional Reinforcement Learning using Characteristic Functions
arXiv:2611.25208v1 Announce Type: new
Abstract: Distributional Reinforcement Learning methods aim to learn the entire distribution of returns, yet current algorithmic approaches are limited to a narrow class of distributions. We propose $\varphi$TD, a method to overcome this limitation by computing the loss in the frequency domain. We demonstrate that this further unifies quantile and categorical approaches to distributional RL, and enables the learning of distributions that were previously impossible to capture, such as mixtures of continuous distributions. We empirically study $\varphi$TD, across synthetic benchmarks and large-scale deep RL environments and demonstrate that the flexibility obtained from wider parametric families can lead to improved performance.
Original source
This story was published by arXiv cs.LG and written by Thomas Mousseau, Tyler Kastner, Davide Baldelli, Amir-massoud Farahmand. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


