Next Article in Journal
Forecasting Electricity Prices: A Machine Learning Approach
Previous Article in Journal
A Novel Hybrid Metaheuristic Algorithm for Optimization of Construction Management Site Layout Planning
Open AccessArticle

Distributional Reinforcement Learning with Ensembles

Department of Mathematics, Linnæus University, 351 95 Växjö, Sweden
*
Author to whom correspondence should be addressed.
Algorithms 2020, 13(5), 118; https://doi.org/10.3390/a13050118
Received: 8 April 2020 / Revised: 23 April 2020 / Accepted: 30 April 2020 / Published: 7 May 2020
(This article belongs to the Section Evolutionary Algorithms and Machine Learning)
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. View Full-Text
Keywords: distributional reinforcement learning; multiagent learning; ensembles; categorical reinforcement learning distributional reinforcement learning; multiagent learning; ensembles; categorical reinforcement learning
Show Figures

Figure 1

  • Externally hosted supplementary file 1
    Doi: 10.5281/zenodo.3742687
    Link: https://doi.org/10.5281/zenodo.3742687
    Description: Source code along with data generated on five Atari 2600 games.
MDPI and ACS Style

Lindenberg, B.; Nordqvist, J.; Lindahl, K.-O. Distributional Reinforcement Learning with Ensembles. Algorithms 2020, 13, 118.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop