DMCA
Diversity-Driven Selection of Exploration Strategies in Multi-Armed Bandits
BibTeX
@MISC{Benureau_diversity-drivenselection,
author = {Fabien Benureau and Inria Bordeaux Sud-ouest and Flowers Team and Ensta Paristech and Pierre-yves Oudeyer and Inria Bordeaux Sud-ouest and Flowers Team and Ensta Paristech},
title = {Diversity-Driven Selection of Exploration Strategies in Multi-Armed Bandits},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract—We consider a scenario where an agent has multiple available strategies to explore an unknown environment. For each new interaction with the environment, the agent must select which exploration strategy to use. We provide a new strategy-agnostic method that treat the situation as a Multi-Armed Bandits problem where the reward signal is the diversity of effects that each strategy produces. We test the method empirically on a simulated planar robotic arm, and establish that the method is both able discriminate between strategies of dissimilar quality, even when the differences are tenuous, and that the resulting performance is competitive with the best fixed mixture of strategies. I.
