ECJ-INTEREST-L Archives

February 2008

ECJ-INTEREST-L@LISTSERV.GMU.EDU

Options: Use Proportional Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Sean Luke <[log in to unmask]>
Reply To:
ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Date:
Wed, 13 Feb 2008 18:20:09 -0500
Content-Type:
text/plain
Parts/Attachments:
text/plain (105 lines)
1. Don't worry about the truncated file.  It's only 67 lines long and  
ECJ is expecting to build a 100x100 grid out of it.  The trail is  
correct -- it's only in the top-left corner of the 100x100 space.   
See P. 157 of Koza's Genetic Programming for an illustration.

2. You should expect the Los Altos Hills trail to be much *much* more  
difficult than the standard Santa Fe trail.

3. Trivia of the day: I believe the Los Altos Hills is where John  
Koza's house is.

Sean



On Feb 13, 2008, at 6:03 PM, Martin V. wrote:

> Hello.
>
> I am having trouble finding ideal individual with Los Altos trail.
> Also the following warning appears at the beginning of the run:
>
> "WARNING:
> Ant trail file ended prematurely"
>
> The command I use to run the ant problem is:
>
> java ec.Evolve -file ant.params -p eval.problem.file=losaltos.trl - 
> p eval.problem.moves=600 -p seed.0=time
>
> The output is:
>
> Threads:  breed/1 eval/1
> Seed: 352523842
> Job: 0
> Setting up
> Processing GP Types
> Processing GP Node Constraints
> Processing GP Function Sets
> Processing GP Tree Constraints
> WARNING:
> Ant trail file ended prematurely
> Initializing Generation 0
> Generation 1
> Generation 2
> Generation 3
> Generation 4
> Generation 5
> Generation 6
> Generation 7
> Generation 8
> Generation 9
> Generation 10
> Generation 11
> Generation 12
> Generation 13
> Generation 14
> Generation 15
> Generation 16
> Generation 17
> Generation 18
> Generation 19
> Generation 20
> Generation 21
> Generation 22
> Generation 23
> Generation 24
> Generation 25
> Generation 26
> Generation 27
> Generation 28
> Generation 29
> Generation 30
> Generation 31
> Generation 32
> Generation 33
> Generation 34
> Generation 35
> Generation 36
> Generation 37
> Generation 38
> Generation 39
> Generation 40
> Generation 41
> Generation 42
> Generation 43
> Generation 44
> Generation 45
> Generation 46
> Generation 47
> Generation 48
> Generation 49
> Generation 50
>
> I tried to run this about 20 times and always the same results and  
> no ideal individual found. :(
>
> Anybody knows if this is the problem in losaltos.trl file or some  
> parameter is set incorrectly?
>
> Thanks for help.
>
> Regards,
> Martin

ATOM RSS1 RSS2