Learning cost-efficient control policies with XCSF: generalization capabilities and further improvement

Authors:
Didier Marin;Jérémie Decock;Lionel Rigoux;Olivier Sigaud
Affiliations:
Institut des Systèmes Intelligents et de Robotique, Paris, France;Institut des Systèmes Intelligents et de Robotique, Paris, France;Institut des Systèmes Intelligents et de Robotique, Paris, France;Institut des Systèmes Intelligents et de Robotique, Paris, France
Venue:
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Year:
2011

Citing 13
Cited 0

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Machine Learning
Dynamic Programming and Optimal Control

Dynamic Programming and Optimal Control
Classifiers that approximate functions

Natural Computing: an international journal
XCS and GALE: A Comparative Study of Two Learning Classifier Systems on Data Mining

IWLCS '01 Revised Papers from the 4th International Workshop on Advances in Learning Classifier Systems
Learning tetris using the noisy cross-entropy method

Neural Computation
Matplotlib: A 2D Graphics Environment

Computing in Science and Engineering
XCSF with computed continuous action

Proceedings of the 9th annual conference on Genetic and evolutionary computation
Classifier fitness based on accuracy

Evolutionary Computation
2008 Special Issue: Reinforcement learning of motor skills with policy gradients

Neural Networks
Context-dependent predictions and cognitive arm control with XCSF

Proceedings of the 10th annual conference on Genetic and evolutionary computation
Control of redundant robots using learned models: an operational space control approach

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
A comparative study: function approximation with LWPR and XCSF

Proceedings of the 12th annual conference companion on Genetic and evolutionary computation
Toward a theory of generalization and learning in XCS

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper we present a method based on the "learning from demonstration" paradigm to get a cost-efficient control policy in a continuous state and action space. The controlled plant is a two degrees-of-freedom planar arm actuated by six muscles. We learn a parametric control policy with XCSF from a few near-optimal trajectories, and we study its capability to generalize over the whole reachable space. Furthermore, we show that an additional Cross-Entropy Policy Search method can improve the global performance of the parametric controller.