Reinforcement learning of motor skills with policy gradients

  • Peters J
  • Schaal S
  • 382

    Readers

    Mendeley users who have this article in their library.
  • 245

    Citations

    Citations of this article.

Abstract

Autonomous learning is one of the hallmarks of human and animal behavior, and understanding the principles of learning will be crucial in order to achieve true autonomy in advanced machines like humanoid robots. In this paper, we examine learning of complex motor skills with human-like limbs. While supervised learning can offer useful tools for bootstrapping behavior, e.g., by learning from demonstration, it is only reinforcement learning that offers a general approach to the final trial-and-error improvement that is needed by each individual acquiring a skill. Neither neurobiological nor machine learning studies have, so far, offered compelling results on how reinforcement learning can be scaled to the high-dimensional continuous state and action spaces of humans or humanoids. Here, we combine two recent research developments on learning motor control in order to achieve this scaling. First, we interpret the idea of modular motor control by means of motor primitives as a suitable way to generate parameterized control policies for reinforcement learning. Second, we combine motor primitives with the theory of stochastic policy gradient learning, which currently seems to be the only feasible framework for reinforcement learning for humanoids. We evaluate different policy gradient methods with a focus on their applicability to parameterized motor primitives. We compare these algorithms in the context of motor primitive learning, and show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. © 2008 Elsevier Ltd. All rights reserved.

Author-supplied keywords

  • Motor primitives
  • Motor skills
  • Natural Actor-Critic
  • Natural gradients
  • Policy gradient methods
  • Reinforcement learning

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Get full text

Authors

  • Jan Peters

  • Stefan Schaal

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free