@InProceedings{lang-toussaint-kersting-10ecml,
  TITLE     = {Exploration in Relational Worlds},
  AUTHOR    = {Lang, T. and Toussaint, M. and Kersting, K.},
  BOOKTITLE = {Proc.~of the European Conf.~on Machine Learning (ECML)},
  YEAR      = {2010},
  MONTH     = {September},
  PDFURL    = {http://www.user.tu-berlin.de/lang/pub/lang-toussaint-kersting-10ecml.pdf},
  ABSTRACT  = { One of the key problems in model-based reinforcement learning is balancing
exploration and exploitation. Another is learning and acting in large relational
domains, in which there is a varying number of objects and relations between
them. We provide one of the first solutions to exploring large
relational Markov decision processes by developing relational extensions of the
concepts of the Explicit Explore or Exploit algorithm. A key insight is
that the inherent generalization of learnt knowledge in the relational
representation has profound implications also on the exploration
strategy: what in a propositional setting would be considered a novel
situation and worth exploration may in the relational setting be an
instance of a well-known context in which exploitation is
promising. Our experimental evaluation shows the effectiveness and
benefit of relational exploration over several propositional benchmark
approaches on noisy 3D simulated robot manipulation problems.},
}