Exploring the Predictable

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@InCollection{Schmidhuber:2002:AEC,
  author =       "Juergen Schmidhuber",
  title =        "Exploring the Predictable",
  booktitle =    "Advances in Evolutionary Computing",
  publisher =    "Springer",
  year =         "2002",
  editor =       "S. Ghosh and S. Tsutsui",
  pages =        "579--612",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "ftp://ftp.idsia.ch/pub/juergen/explorepredictable.pdf",
  URL =          "http://www.idsia.ch/~juergen/explorepredictable/",
  abstract =     "Details of complex event sequences are often not
                 predictable, but their reduced abstract representations
                 are. I study an embedded active learner that can limit
                 its predictions to almost arbitrary computable aspects
                 of spatio-temporal events. It constructs probabilistic
                 algorithms that (1) control interaction with the world,
                 (2) map event sequences to abstract internal
                 representations (IRs), (3) predict IRs from IRs
                 computed earlier. Its goal is to create novel
                 algorithms generating IRs useful for correct IR
                 predictions, without wasting time on those learned
                 before. This requires an adaptive novelty measure which
                 is implemented by a co-evolutionary scheme involving
                 two competing modules collectively designing (initially
                 random) algorithms representing experiments. Using
                 special instructions, the modules can bet on the
                 outcome of IR predictions computed by algorithms they
                 have agreed upon. If their opinions differ then the
                 system checks who's right, punishes the loser (the
                 surprised one), and rewards the winner. An evolutionary
                 or reinforcement learning algorithm forces each module
                 to maximise reward. This motivates both modules to lure
                 each other into agreeing upon experiments involving
                 predictions that surprise it. Since each module
                 essentially can veto experiments it does not consider
                 profitable, the system is motivated to focus on those
                 computable aspects of the environment where both
                 modules still have confident but different opinions.
                 Once both share the same opinion on a particular issue
                 (via the loser's learning process, e.g., the winner is
                 simply copied onto the loser), the winner loses a
                 source of reward -- an incentive to shift the focus of
                 interest onto novel experiments. My simulations include
                 an example where surprise-generation of this kind helps
                 to speed up external reward.",
}

Genetic Programming entries for Jurgen Schmidhuber

Citations