Prediction and Control in an Active Environment

  • Alan J. MacDonald
Part of the The Kluwer International Series in Engineering and Computer Science book series (SECS, volume 12)


The definition of a mechanism which learns to predict the consequences of events and actions in an environment is in progress. Salient features of this research include an attempt to separate prior assumptions (bias) from the learning algorithm proper and, as far as possible, to make them explicit. The emphasis is on events rather than objects — the input from the environment is is not restricted to be a succession of object and relation oriented descriptions of environmental state. Of particular interest is the acquisition of such object based representations. The task domain (learning to predict in a particular class of environments) is defined with these aims in mind.


Cellular Automaton Event History Label Graph Prior Assumption Neighbourhood Relation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Kluwer Academic Publishers 1986

Authors and Affiliations

  • Alan J. MacDonald
    • 1
  1. 1.Kobler Unit, Dept ComputingImperial CollegeLondonEngland

Personalised recommendations