Informatics Report Series



Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Title:Reinforcement Learning for Humanoid Robots - Policy Gradients and Beyond
Authors: Sethu Vijayakumar ; Jan Peters ; Stefan Schaal
Date:Jul 2004
Reinforcement learning offers one of the most general frameworks to take traditional robotics towards true autonomy and versatility. However, applying reinforcement learning to high dimensional movement systems like humanoid robots remains an unsolved problem. In this paper, we discuss different approaches of reinforcement learning in terms of their applicability in humanoid robotics. Methods can be coarsely classified in to three different categories, i.e., greedy methods, 'vanilla' policy gradient methods, and natural gradient methods. We discuss that greedy methods are not likely to scale into the domain humanoid robotics as they are problematic when used with function approximation. Vanilla' policy gradient methods on the other hand have been successfully applied on real-world robots including at least one humanoid robot [3]. We demonstrate that these methods can be significantly improved using the natural policy gradient instead of the regular policy gradient. A derivation of the natural policy gradient is provided, proving that the average policy gradient of Kakade[10] is indeed the true natural gradient. A general algorithm for estimating the natural gradient, the Natural Actor-Critic algorithm, is introduced. This algorithm converges to the nearest local minimum of the cost function with respect to the Fisher information metric under suitable conditions. The algorithm outperforms non-natural policy gradients by far in a cart-pole balancing evaluation, and for learning non-linear dynamic motor primitives for humanoid robot control. It offers a promising route for the development of reinforcement learning for truly high-dimensionally continuous state-action systems.
2004 by The University of Edinburgh. All Rights Reserved
Links To Paper
No links available
Bibtex format
author = { Sethu Vijayakumar and Jan Peters and Stefan Schaal },
title = {Reinforcement Learning for Humanoid Robots - Policy Gradients and Beyond},
year = 2004,
month = {Jul},

Home : Publications : Report 

Please mail <> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh