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

Fabien Benureau (1) , Pierre-Yves Oudeyer (1)

1 Flowers - Flowing Epigenetic Robots and Systems

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.

Mots clés: exploration; active learning; diversity; evolutionary computation; developmental robotics; multi-armed bandits

Domaines: Intelligence artificielle [cs.AI]; Robotique [cs.RO]; Apprentissage [cs.LG]

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⟩