In this section
@book{Deisenroth:2013:10.1561/2300000021,
author = {Deisenroth, MP and Neumann, G and Peters, J},
doi = {10.1561/2300000021},
publisher = {now Publishers},
title = {A Survey on Policy Search for Robotics},
url = {http://dx.doi.org/10.1561/2300000021},
year = {2013}
}
TY - BOOK
AB - Policy search is a subfield in reinforcement learning which focuses onfinding good parameters for a given policy parametrization. It is wellsuited for robotics as it can cope with high-dimensional state and actionspaces, one of the main challenges in robot learning. We review recentsuccesses of both model-free and model-based policy search in robotlearning.Model-free policy search is a general approach to learn policiesbased on sampled trajectories. We classify model-free methods based ontheir policy evaluation strategy, policy update strategy, and explorationstrategy and present a unified view on existing algorithms. Learning apolicy is often easier than learning an accurate forward model, and,hence, model-free methods are more frequently used in practice. How-ever, for each sampled trajectory, it is necessary to interact with the robot, which can be time consuming and challenging in practice. Model-based policy search addresses this problem by first learning a simulatorof the robot’s dynamics from data. Subsequently, the simulator gen-erates trajectories that are used for policy learning. For both model-free and model-based policy search methods, we review their respectiveproperties and their applicability to robotic systems.
AU - Deisenroth,MP
AU - Neumann,G
AU - Peters,J
DO - 10.1561/2300000021
PB - now Publishers
PY - 2013///
TI - A Survey on Policy Search for Robotics
UR - http://dx.doi.org/10.1561/2300000021
ER -