Publication Details

SELECT * FROM publications WHERE Record_Number=10271
Reference TypeJournal Article
Author(s)Peters, J.; Schaal, S.
TitleReinforcement learning of motor skills with policy gradients
Journal/Conference/Book TitleNeural Networks
KeywordsReinforcement learning, Policy gradient methods, Natural gradients, Natural Actor-Critic, Motor skills, Motor primitives
AbstractAutonomous 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.
Short TitleReinforcement learning of motor skills with policy gradients
ISBN/ISSN0893-6080 (Print)
Accession Number18482830
AddressMax Planck Institute for Biological Cybernetics, Spemannstr. 38, 72076 Tubingen, Germany; University of Southern California, 3710 S. McClintoch Ave-RTH401, Los Angeles, CA 90089-2905, USA.


zum Seitenanfang