Skip to Main content Skip to Navigation
Conference papers

Diversity-driven selection of exploration strategies in multi-armed bandits

Fabien Benureau 1, * Pierre-Yves Oudeyer 1
* Corresponding author
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
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.
Complete list of metadatas

Cited literature [36 references]  Display  Hide  Download

https://hal.inria.fr/hal-01251060
Contributor : Pierre-Yves Oudeyer <>
Submitted on : Tuesday, January 5, 2016 - 3:38:24 PM
Last modification on : Friday, March 6, 2020 - 2:14:41 AM
Long-term archiving on: : Thursday, April 7, 2016 - 3:28:44 PM

File

BenureauOudeyerIcdl2015.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Fabien Benureau, Pierre-Yves Oudeyer. Diversity-driven selection of exploration strategies in multi-armed bandits. IEEE International Conference on Development and Learning and Epigenetic Robotics, Aug 2015, Providence, United States. ⟨10.1109/DEVLRN.2015.7346130⟩. ⟨hal-01251060⟩

Share

Metrics

Record views

262

Files downloads

575