---
title: "Reinforcement Learning to Adjust Robot Movements to New Situations"
authors:
  - "Jens Kober"
  - "Erhan Öztop"
  - "Jan Peters"
doi: "10.5591/978-1-57735-516-8/IJCAI11-441"
url: "https://ijcai.org/proceedings/2011/441"
pdf: "https://ijcai.org/proceedings/2011/0441.pdf"
venue: "Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence"
year: 2011
pages: "2650-2654"
track: ""
keywords:
---

# Reinforcement Learning to Adjust Robot Movements to New Situations

Jens Kober, Erhan Öztop, Jan Peters

*Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence*, pages 2650-2654. DOI: [10.5591/978-1-57735-516-8/IJCAI11-441](https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-441)

## Abstract

Many complex robot motor skills can be represented using elementary movements, and there exist efficient techniques for learning parametrized motor plans using demonstrations and self-improvement. However with current techniques, in many cases, the robot currently needs to learn a new elementary movement even if a parametrized motor plan exists that covers a related situation. A method is needed that modulates the elementary movement through the meta-parameters of its representation. In this paper, we describe how to learn such mappings from circumstances to meta-parameters using reinforcement learning. In particular we use a kernelized version of the reward-weighted regression. We show two robot applications of the presented setup in robotic domains; the generalization of throwing movements in darts, and of hitting movements in table tennis. We demonstrate that both tasks can be learned successfully using simulated and real robots.