Bayesian Optimization with Automatic Prior Selection for Data-Efficient Direct Policy Search

Rémi Pautrat 1 Konstantinos Chatzilygeroudis 1 Jean-Baptiste Mouret 1
1 LARSEN - Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : One of the most interesting features of Bayesian optimization for direct policy search is that it can leverage priors (e.g., from simulation or from previous tasks) to accelerate learning on a robot. In this paper, we are interested in situations for which several priors exist but we do not know in advance which one fits best the current situation. We tackle this problem by introducing a novel acquisition function, called Most Likely Expected Improvement (MLEI), that combines the likelihood of the priors and the expected improvement. We evaluate this new acquisition function on a transfer learning task for a 5-DOF planar arm and on a possibly damaged, 6-legged robot that has to learn to walk on flat ground and on stairs, with priors corresponding to different stairs and different kinds of damages. Our results show that MLEI effectively identifies and exploits the priors, even when there is no obvious match between the current situations and the priors.
Complete list of metadatas

Cited literature [44 references]  Display  Hide  Download

https://hal.inria.fr/hal-01768279
Contributor : Jean-Baptiste Mouret <>
Submitted on : Tuesday, April 17, 2018 - 10:14:11 AM
Last modification on : Tuesday, December 18, 2018 - 4:40:22 PM

File

1709.06919.pdf
Files produced by the author(s)

Identifiers

Citation

Rémi Pautrat, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret. Bayesian Optimization with Automatic Prior Selection for Data-Efficient Direct Policy Search. ICRA 2018 - International Conference on Robotics and Automation, May 2018, Brisbane, Australia. ⟨hal-01768279⟩

Share

Metrics

Record views

202

Files downloads

232