Display Publications by [Year] [Type] [Topic]
In multiagent problems that require complex joint actions, reward shaping methods yield good behavior by incentivizing the agentsŐ potentially valuable actions. However, reward shaping often re- quires access to the functional form of the reward function and the global state of the system. In this work, we introduce the Exploratory Gaussian Reward (EGR), a new reward model that creates optimistic stepping stone rewards linking the agents potentially good actions to the desired joint action. EGR models the system reward as a Gaussian Process to leverage the inherent uncertainty in reward estimates that push agents to explore unobserved state space. In the tightly coupled rover coordination problem, we show that EGR significantly outperforms a neural network approximation baseline and is comparable to the system with access to the functional form of the global reward. Finally, we demonstrate how EGR improves performance over other reward shaping methods by forcing agents to explore and escape local optima.
@InProceedings{tumer-dixit_aamas20,
author = {G. Dixit and S. Airiau and K. Tumer},
title = {Gaussian Processes as Multiagent Reward Models},
booktitle = {Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems},
address = {Auckland, New Zealand},
month = {May},
pages={},
abstract={In multiagent problems that require complex joint actions, reward shaping methods yield good behavior by incentivizing the agentsÕ potentially valuable actions. However, reward shaping often re- quires access to the functional form of the reward function and the global state of the system. In this work, we introduce the Exploratory Gaussian Reward (EGR), a new reward model that creates optimistic stepping stone rewards linking the agents potentially good actions to the desired joint action. EGR models the system reward as a Gaussian Process to leverage the inherent uncertainty in reward estimates that push agents to explore unobserved state space. In the tightly coupled rover coordination problem, we show that EGR significantly outperforms a neural network approximation baseline and is comparable to the system with access to the functional form of the global reward. Finally, we demonstrate how EGR improves performance over other reward shaping methods by forcing agents to explore and escape local optima.},
bib2html_pubtype = {Refereed Conference Papers},
bib2html_rescat = {Multiagent Systems, Evolutionary Algorithms},
year = {2020}
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 01, 2020 17:39:43