Transfer of knowledge for a climbing virtual human: a reinforcement learning approach

Authors:
Benoît Libeau;Alain Micaelli;Olivier Sigaud
Affiliations:
Laboratoire d'Intégration des Systèmes et des Technologies in Commissariat à l'Énergie Atomique, France;Laboratoire d'Intégration des Systèmes et des Technologies in Commissariat à l'Énergie Atomique, France;Institut des Systèmes Intelligents et de Robotique, Université Pierre et Marie Curie - Paris 6, CNRS, UMR, Paris Cedex 05, France
Venue:
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Year:
2009

Citing 6
Cited 0

Integrated architecture for learning, planning, and reacting based on approximating dynamic programming

Proceedings of the seventh international conference (1990) on Machine learning
Technical Note: \cal Q-Learning

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Synthesis of complex dynamic character motion from simple animations

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Autonomous shaping: knowledge transfer in reinforcement learning

ICML '06 Proceedings of the 23rd international conference on Machine learning
Near-optimal character animation with continuous control

ACM SIGGRAPH 2007 papers

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the reinforcement learning literature, transfer is the capability to reuse on a new problem what has been learnt from previous experiences on similar problems. Adapting transfer properties for robotics is a useful challenge because it can reduce the time spent in the first exploration phase on a new problem. In this paper we present a transfer framework adapted to the case of a climbing Virtual Human (VH). We show that our VH learns faster to climb a wall after having learnt on a different previous wall.