Imperial College London


Faculty of EngineeringDyson School of Design Engineering




+44 (0)20 7594 9235p.kormushev Website




156Roderic Hill BuildingSouth Kensington Campus






BibTex format

author = {Leonetti, M and Kormushev, P and Sagratella, S},
doi = {10.2478/cait-2012-0021},
journal = {Cybernetics and Information Technologies},
pages = {53--65},
title = {Combining local and global direct derivative-free optimization for reinforcement learning},
url = {},
volume = {12},
year = {2012}

RIS format (EndNote, RefMan)

AB - We consider the problem of optimization in policy space for reinforcement learning. While a plethora of methods have been applied to this problem, only a narrow category of them proved feasible in robotics. We consider the peculiar characteristics of reinforcement learning in robotics, and devise a combination of two algorithms from the literature of derivative-free optimization. The proposed combination is well suited for robotics, as it involves both off-line learning in simulation and on-line learning in the real environment. We demonstrate our approach on a real-world task, where an Autonomous Underwater Vehicle has to survey a target area under potentially unknown environment conditions. We start from a given controller, which can perform the task under foreseeable conditions, and make it adaptive to the actual environment.
AU - Leonetti,M
AU - Kormushev,P
AU - Sagratella,S
DO - 10.2478/cait-2012-0021
EP - 65
PY - 2012///
SN - 1311-9702
SP - 53
TI - Combining local and global direct derivative-free optimization for reinforcement learning
T2 - Cybernetics and Information Technologies
UR -
UR -
VL - 12
ER -