Path Integral Policy Improvement with Covariance Matrix Adaptation

Freek Stulp (1, 2) , Olivier Sigaud (3)

1 Flowers - Flowing Epigenetic Robots and Systems
2 RV - Robotique et Vision
3 ISIR - Institut des Systèmes Intelligents et de Robotique

There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parameterized policies. PI2 is a recent example of this approach. It combines a derivation from first principles of stochastic optimal control with tools from statistical estimation theory. In this paper, we consider PI2- as a member of the wider family of methods which share the concept of probability-weighted averaging to iteratively update parameters to optimize a cost function. At the conceptual level, we compare PI2 to other members of the same family, being Cross-Entropy Methods and CMAES. The comparison suggests the derivation of a novel algorithm which we call PI2-CMA for ''Path Integral Policy Improvement with Covariance Matrix Adaptation''. PI2-CMA's main advantage is that it determines the magnitude of the exploration noise automatically

Domaines: Robotique [cs.RO]

Freek Stulp, Olivier Sigaud. Path Integral Policy Improvement with Covariance Matrix Adaptation. Proceedings of the 29th International Conference on Machine Learning (ICML), Jun 2012, Edinbourg, United Kingdom. pp.0-0. ⟨hal-00789391⟩