Community Research and Development Information Service - CORDIS


This paper describes an architecture which deals effectively with complex high-dimensional and/or continuous situation and action spaces. This architecture is based on two main ideas. The first is to organise the reactive component into a set of modules in such a way that each one of them codifies the prototypical action for a given cluster of situations. The second idea is to use a particular kind of planning for figuring out what part of the action space deserves attention for each cluster of situations. Salient features of the planning process are that it is grounded and that it is invoked only when the reactive component does not generalise correctly its previous experience to the new situation.

Additional information

Authors: MILLAN J DEL R, JRC Ispra (IT)
Bibliographic Reference: Article: Robotics and Autonomous Systems : Reinforcement Learning in Robotics (1995)
Record Number: 199511172 / Last updated on: 1995-08-23
Original language: en
Available languages: en