Display Publications by [Year] [Type] [Topic]
Distributed agents concurrently learning to coordinate in a multiagent system can suffer from considerable amounts of agent noise. This is the noise that arises from the non-stationarity of the learn- ing environment for each individual agent since other agents in the system are also constantly updating their policies, thereby continually shifting the goal posts for successful coordination. In this work, we propose a method to reduce agent noise by allowing individual agents to probabilistically determine whether or not to undergo policy updates based on their estimated impact on the team learning performance. We show that using this method to adapt the number of actively learning agents over time provides improvements to the convergence speed of the team as a whole without affecting the final converged learning performance.
(unavailable)
@inproceedings{tumer-chung_aamas18,
author = {J. J. Chung and S. Chow and K. Tumer},
title = {When less is more: Reducing agent noise with probabilistically learning agents (Extended Abstract)},
booktitle = {Proceedings of the Seventeenth International Joint Conference on Autonomous Agents and Multiagent Systems},
month = {July},
pages ={},
address = {Stockholm, Sweden},
abstract={Distributed agents concurrently learning to coordinate in a multiagent system can suffer from considerable amounts of agent noise. This is the noise that arises from the non-stationarity of the learn- ing environment for each individual agent since other agents in the system are also constantly updating their policies, thereby continually shifting the goal posts for successful coordination. In this work, we propose a method to reduce agent noise by allowing individual agents to probabilistically determine whether or not to undergo policy updates based on their estimated impact on the team learning performance. We show that using this method to adapt the number of actively learning agents over time provides improvements to the convergence speed of the team as a whole without affecting the final converged learning performance.},
bib2html_pubtype = {Refereed Conference Papers},
bib2html_rescat = {Multiagent Systems},
year = {2018}
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 01, 2020 17:39:43