Hi everyone,<div><br></div><div>I&#39;m using the Grammatical Evolution (GE) package in ECJ (ec.gp.ge.*) to evolve the control structure of an agent in a multi-agent system. This approach seems to be working fairly well. However, my choice for using GE was rather arbitrary and I would like to compare my current implementation using GE to other GGGP (Grammar Guided GP) solutions.</div>
<div><br></div><div>The reason that I want to conduct this comparison is because I&#39;m in doubt if GE is the best representation for my problem. For example, in [1] GE is outperformed by GP on the Santa Fe Ant Trail problem. Because the Santa Fe Ant Trail problem is in the agent domain, I suspect that GP might be better for my agent problem as well.</div>
<div><br></div><div>There are two GGGP representations which I would like to use in my implementation, and therefore in ECJ. One is &#39;plain&#39; grammar guided GP and the other is tree adjoining grammars (TAG). According to [2], one of the benefits of using TAGs is: &quot;The TAG transformation permits local dependencies in the genotype space to map to long-distance dependencies in the intermediate phenotype space in a controlled way, corresponding to the structure of the grammar.&quot;</div>
<div><br></div><div>In short my questions are:</div><div><ul><li>Does the above reasoning for researching other grammar based GP representations make sense, or am I missing the point (or some recent literature)?</li><li>Are there other GGGP implementations in ECJ besides GE, such as plain GGGP and TAG? If not, why?</li>
</ul></div><div>If other GGGP implementations do not exist, I&#39;m thinking of developing them as extensions to ECJ in the future.</div><div><br></div><div>1.<span> </span>OʼNeill, M. and Ryan, C. Grammatical Evolution. <i>Evolutionary Computation 5</i>, 4 (2001), 349-358.</div>
<div>2.<span> </span>McKay, R.I., Hoai, N.X., Whigham, P.A., Shan, Y., and O’Neill, M. Grammar-based Genetic Programming: a survey. <i>Genetic Programming and Evolvable Machines 11</i>, 3-4 (2010), 365-396.</div><div><br>
</div><div>Best regards,</div><div>Rinde van Lon</div>

<br>
<FONT FACE=3D"Helvetica" SIZE=3D2>Disclaimer: <A HREF="http://www.kuleuven.be/cwis/email_disclaimer.htm">http://www.kuleuven.be/cwis/email_disclaimer.htm</A> for more information.</FONT>
 <BR>