Conference proceedings

Learning to deal with objects

Malfaz M, Salichs M ...see all

2009 IEEE 8th International Conference on Development and Learning, ICDL 2009 (2009)

  • 9


    Mendeley users who have this article in their library.
  • 7


    Citations of this article.
Sign in to save reference


In this paper, a modification of the standard learning algorithm Q-learning is presented: Object Q-learning (OQ-learning). An autonomous agent should be able to decide its own goals and behaviours in order to fulfil these goals. When the agent has no previous knowledge, it must learn what to do in every state (policy of behaviour). If the agent uses Q-learning, this implies that it learns the utility value Q of each action-state pair. Typically, an autonomous agent living in a complex environment has to interact with different objects present in that world. In this case, the number of states of the agent in relation to those objects may increase as the number of objects increases, making the learning process difficult to deal with. The proposed modification appears as a solution in order to cope with this problem. The experimental results prove the usefulness of the OQ-learning in this situation, in comparison with the standard Q-learning algorithm.

Author-supplied keywords

  • Autonomous agents
  • Decision making
  • Objects
  • Q-learning

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Get full text


  • María Malfaz

  • Miguel A. Salichs

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free