Nate Kohl's Publications

Sorted by DateClassified by Publication TypeClassified by Research Category


Evolving Neural Networks for Strategic Decision-Making Problems

Evolving Neural Networks for Strategic Decision-Making Problems. Nate Kohl and Risto Miikkulainen. Neural Networks, 22:326–337, 2009. Special issue on Goal-Directed Neural Systems.

Download

[PDF]340.4kB  

Abstract

Evolution of neural networks, or neuroevolution, has been a successful approach to many low-level control problems such as pole balancing, vehicle control, and collision warning. However, certain types of problems -- such as those involving strategic decision-making -- have remained difficult for neuroevolution to solve. This paper evaluates the hypothesis that such problems are difficult because they are fractured: The correct action varies discontinuously as the agent moves from state to state. A method for measuring fracture using the concept of function variation is proposed, and based on this concept, two methods for dealing with fracture are examined: neurons with local receptive fields, and refinement based on a cascaded network architecture. Experiments in several benchmark domains are performed to evaluate how different levels of fracture affect the performance of neuroevolution methods, demonstrating that these two modifications improve performance significantly. These results form a promising starting point for expanding neuroevolution to strategic tasks.

BibTeX Entry

@Article{kohl:gdns09,
  author = "Nate Kohl and Risto Miikkulainen",
  title = "Evolving Neural Networks for Strategic Decision-Making Problems",
  journal = "Neural Networks",
  year = "2009",
  volume = "22",
  issue = "3",
  pages = "326--337",
  note = "Special issue on Goal-Directed Neural Systems.",
  abstract = {
Evolution of neural networks, or neuroevolution, has been a successful 
approach to many low-level control problems such as pole balancing, 
vehicle control, and collision warning.  However, certain types of 
problems -- such as those involving strategic decision-making -- have 
remained difficult for neuroevolution to solve.  This paper evaluates 
the hypothesis that such problems are difficult because they are 
fractured: The correct action varies discontinuously as the agent 
moves from state to state.  A method for measuring fracture using the 
concept of function variation is proposed, and based on this concept, 
two methods for dealing with fracture are examined: neurons with local 
receptive fields, and refinement based on a cascaded network 
architecture.  Experiments in several benchmark domains are performed 
to evaluate how different levels of fracture affect the performance of 
neuroevolution methods, demonstrating that these two modifications 
improve performance significantly.  These results form a promising 
starting point for expanding neuroevolution to strategic tasks. 
},
  bib2html_pubtype = {Journal},
  bib2html_rescat = {Machine Learning}
}

Generated by bib2html.pl (written by Patrick Riley ) on Sun May 15, 2011 08:27:15