Distributional Reinforcement Learning with Ensembles
Machine Learning
2020-05-25 v2 Artificial Intelligence
Multiagent Systems
Machine Learning
Abstract
It is well known that ensemble methods often provide enhanced performance in reinforcement learning. In this paper, we explore this concept further by using group-aided training within the distributional reinforcement learning paradigm. Specifically, we propose an extension to categorical reinforcement learning, where distributional learning targets are implicitly based on the total information gathered by an ensemble. We empirically show that this may lead to much more robust initial learning, a stronger individual performance level, and good efficiency on a per-sample basis.
Cite
@article{arxiv.2003.10903,
title = {Distributional Reinforcement Learning with Ensembles},
author = {Björn Lindenberg and Jonas Nordqvist and Karl-Olof Lindahl},
journal= {arXiv preprint arXiv:2003.10903},
year = {2020}
}
Comments
15 pages, 2 figures