Learning concurrent motor skills in versatile solution spaces
- 1 October 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3591-3597
- https://doi.org/10.1109/iros.2012.6386047
Abstract
Future robots need to autonomously acquire motor skills in order to reduce their reliance on human programming. Many motor skill learning methods concentrate on learning a single solution for a given task. However, discarding information about additional solutions during learning unnecessarily limits autonomy. Such favoring of single solutions often requires re-learning of motor skills when the task, the environment or the robot's body changes in a way that renders the learned solution infeasible. Future robots need to be able to adapt to such changes and, ideally, have a large repertoire of movements to cope with such problems. In contrast to current methods, our approach simultaneously learns multiple distinct solutions for the same task, such that a partial degeneration of this solution space does not prevent the successful completion of the task. In this paper, we present a complete framework that is capable of learning different solution strategies for a real robot Tetherball task.Keywords
This publication has 16 references indexed in Scilit:
- Movement templates for learning of hitting and battingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Model-free reinforcement learning as mixture learningPublished by Association for Computing Machinery (ACM) ,2009
- Kinesthetic Bootstrapping: Teaching Motor Skills to Humanoid Robots through Physical InteractionLecture Notes in Computer Science, 2009
- Policy Gradient Methods for RoboticsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Learning Sensory Feedback to CPG with Policy Gradient for Biped LocomotionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Autonomous helicopter control using reinforcement learning policy search methodsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learningArtificial Intelligence, 1999
- Is imitation learning the route to humanoid robots?Trends in Cognitive Sciences, 1999
- A View of the Em Algorithm that Justifies Incremental, Sparse, and other VariantsPublished by Springer Science and Business Media LLC ,1998
- Acquiring robot skills via reinforcement learningIEEE Control Systems, 1994