### Abstract

Abstract—A developing agent learns a model of the world

by observing regularities occurring in its sensory inputs. In a

continuous domain where the model is represented by a set of

rules, a significant part of the task of learning such a model is to

find appropriate intervals within the continuous state variables,

such that these intervals can be used to define rules whose

predictions are reliable. We propose a technique to find such

intervals (or regions) by means of finding clusters on approximate

probability distributions of sensory variables. We compare

this cluster-based method with an alternative landmark-based

algorithm. We evaluate both techniques on a data log recorded

in a simulation based on OpenArena, a three-dimensional firstperson-

perspective computer game, and demonstrate the results

of how the techniques can learn rules which describe walking

behaviour. While both techniques work reasonably well, the

clustering approach seems to give more “natural” regions which

correspond more closely to what a human would expect; we

speculate that such regions should be more useful if they are to

form a basis for further learning of higher order rules.

by observing regularities occurring in its sensory inputs. In a

continuous domain where the model is represented by a set of

rules, a significant part of the task of learning such a model is to

find appropriate intervals within the continuous state variables,

such that these intervals can be used to define rules whose

predictions are reliable. We propose a technique to find such

intervals (or regions) by means of finding clusters on approximate

probability distributions of sensory variables. We compare

this cluster-based method with an alternative landmark-based

algorithm. We evaluate both techniques on a data log recorded

in a simulation based on OpenArena, a three-dimensional firstperson-

perspective computer game, and demonstrate the results

of how the techniques can learn rules which describe walking

behaviour. While both techniques work reasonably well, the

clustering approach seems to give more “natural” regions which

correspond more closely to what a human would expect; we

speculate that such regions should be more useful if they are to

form a basis for further learning of higher order rules.

Original language | English |
---|---|

Title of host publication | 2011 IEEE International Conference on Development and Learning (ICDL 2011) |

Publisher | Institute of Electrical and Electronics Engineers (IEEE) |

Pages | n/a |

Number of pages | 8 |

Volume | 2 |

ISBN (Print) | 978-1-61284-989-8 |

DOIs | |

Publication status | Published - 24 Aug 2011 |

Event | International Conference on Development and Learning and Epigenetic Robotics - Frankfurt, Germany Duration: 24 Aug 2011 → … |

### Conference

Conference | International Conference on Development and Learning and Epigenetic Robotics |
---|---|

Country | Germany |

City | Frankfurt |

Period | 24/08/11 → … |

### Fingerprint

### Cite this

Slowinski, W., & Guerin, F. (2011). Learning regions for building a world model from clusters in probability distributions. In

*2011 IEEE International Conference on Development and Learning (ICDL 2011)*(Vol. 2, pp. n/a). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/DEVLRN.2011.6037339