事前分布の自動選択を伴うベイズ最適化によるデータ効率の良い直接方策探索
Bayesian Optimization with Automatic Prior Selection for Data-Efficient Direct Policy Search
複数の事前分布がある状況でどれが最適か分からない問題に対し、事前分布の尤度と期待改善を組み合わせた新獲得関数MLEIを提案し、腕ロボットの転移学習や脚ロボットの歩行学習で有効性を示した。
著者: Rémi Pautrat, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret
分類: cs.RO, cs.AI, cs.LG, cs.NE, stat.ML
原文アブストラクト
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.
