@unpublished{stulp:hal-00738463, TITLE = {{Policy Improvement Methods: Between Black-Box Optimization and Episodic Reinforcement Learning}}, AUTHOR = {Stulp, Freek and Sigaud, Olivier}, URL = {https://hal.archives-ouvertes.fr/hal-00738463}, NOTE = {34 pages}, YEAR = {2012}, MONTH = Oct, HAL_ID = {hal-00738463}, HAL_VERSION = {v1}, }