I followed Pete Mandik's proposal of developing highly connected neuron
arrays and the result was great. Previously I had attempted to measure and
solve motion and direction changes manually through analog design. I even
tried using split brain control, but usually just got frustrated with not
solving the problem manually. Using large random brain connections was
always an idea in the back of my brain but I couldn't keep the direction
minimized. I was never able to get the success I acheived with Pete's idea.
This took two days. I'd like to see what others can do with different
designs. I'm sticking with the "frog", because I love to watch it hop :)
simulation configuration is at the end. ball energy must be 1000 for this
to work.
here is the starting genome. it should be easy to read.
3x3-array-frog
(X[S:1][|5:0][@5:0],
X[S:1][|2:0][@4:0],
X[1:0,2:0,3:0,4:0,5:0,6:0,7:0,8:0][-1:0,1:0,2:0,3:0,4:0,5:0,6:0,7:0][-8:0,-2
:0,-1:0,1:0,2:0,3:0,4:0,5:0,6:0,12:0][-3:0,-2:0,-1:0,1:0,2:0,3:0,4:0,5:0][-4
:0,-3:0,-2:0,-1:0,1:0,2:0,3:0,4:0][-5:0,-4:0,-3:0,-2:0,-1:0,1:0,2:0,3:0][-9:
0,-6:0,-5:0,-4:0,-3:0,-2:0,-1:0,1:0,2:0,5:0][-7:0,-6:0,-5:0,-4:0,-3:0,-2:0,-
1:0,1:0][-8:0,-7:0,-6:0,-5:0,-4:0,-3:0,-2:0,-1:0],
X[@-4:1][|-2:1][S:1],
X[@-5:1][|-5:1][S:1])
And here is #46020 (just hops in right hand circles but maybe some more work
will get me left turns )
(X[S:2.549][|5:-4.307][@5:2.745],X[S:-0.709][|2:4.837][@4:1.967],X[1:-940.28
2,2:4.319,3:-1.170,4:-2.753,5:2.990,6:-3.702,7:546.450,8:-2.261][-1:2.608,1:
4.475,2:994.061,3:-0.673,4:-0.418,5:-1.868,6:-1.027,7:0.766][-8:2.687,-2:1.5
17,-1:-0.886,1:-3.607,2:-1.182,3:2.942,4:1.585,5:467.428,6:-2.159,12:-2.736]
[-3:1.075,-2:2.002,-1:-107.619,1:-606.327,2:-0.982,3:-2.646,4:2.481,5:3.018]
[-4:-1.387,-3:-2.697,-2:1.411,-1:0.698,1:1.234,2:4.168,3:1.040,4:-0.485][-5:
0.894,-4:2.095,-3:1.203,-2:-3.348,-1:0.301,1:-1.279,2:-2.534,3:4.617][-9:1.6
67,-6:3.096,-5:-1.507,-4:-4.053,-3:1.877,-2:2.319,-1:-413.892,1:0.982,2:1.84
1,5:-428.160][-7:-1.828,-6:-564.315,-5:-0.836,-4:-2.225,-3:1.243,-2:3.121,-1
:-2.908,1:4.560][-8:-2.323,-7:2.052,-6:2.405,-5:-943.026,-4:1.697,-3:1.279,-
2:-1.344,-1:744.677],X[@-4:1][|-2:-1.038][S:-0.932],X[@-5:0.643][|-5:1.470][
S:-836.992])
as a comparison..here is a single neuron array frog that also finds food..
(mostly)
(X[|5:1.324][@4:985.403][@S:-2.868],X[S:-4.397][|1:-0.450],X[=:-0.617,-2:21.
341,-3:-261.030,-4:248.531,-5:-4.340,!:0.599,=:0.970,1:-392.186,2:267.372,3:
1.072,3 :-2.272,5:-4.865],X[|-1:1.150][S:-1.930],X[S:3.585,1
:5.858][@-4:-1.549][|-5:-322.309])
change-neuron-weight-only.sim
# created Fri Oct 12 17:48:03 2001
# by Framsticks simulator (30-May-00) [MS Windows]
sim_params:
model:1
oldneurons:0
capacity:200
delrule:0
descol:0
debug:0
AutoKill:1
cr_c:0
cr_life:0
cr_v:0
cr_gl:0
cr_nnsiz:0
cr_di:1
cr_vpos:0
cr_vvel:0
cr_norm:1
fitfun:0
fitm:2
fitma:5
enablestats:2
cr_simi:0
testvel:9
cr_energ:0
MaxCreated:1
p_nop:10
p_mut:90
p_xov:0
xov_mins:0
Energy0:100
grow:0
corpsen:0
e_meta:1
aging:0
em_stat:0
em_dyn:0
sun:0
feed:4
feede0:1000
autosave:20
overwrite:1
filecomm:0
wrldtyp:0
wrldsiz:50
wrldmap:
wrldwat:-1
wrldbnd:0
mut_str:0
mut_neu:20
mut_exmod:eE
mut_exrec:S
mut_exctl:
gm_repair:1
gm_xosegm:1
geno_f1_sm0:0.05
geno_f1_sm1:0.02
geno_f1_sm2:0.02
geno_f1_sm3:0.02
geno_f1_sm4:0.1
geno_f1_nm0:1
geno_f1_nm1:0
geno_f1_nm2:0
geno_f1_nm3:0
geno_f1_nm4:0
geno_f1_nm5:0
geno_f1_simNN:1
geno_f1_simSN:1
geno_f1_simSS:1
geno_f1_simNS:1
geno_f1_simStr:4
geno_f4_mut1add:0.5
geno_f4_mut1del:0.2
geno_f4_mutAdd2div:0.2
geno_f4_mutAdd2link:0.2
geno_f4_mutAdd2rep:0.1
genkonw0:1
genkonw1:1
genkonw2:1
genkonw3:1
Re: Food Finding Frogs
Zac, I'm delighted to read of your recent successes using my "BigBrain"
approach. Below are some additional designs BrainyFrog and Insecty.
BrainyFrog's body is essentially your frog. Insecty's body was created by
one of my Cognitive Science students, Shawn Gaston.
What I did with the brains here is slightly different. There are
feedforward connections from sensors to hidden layers and from hidden layers
to the motors. The only recurrence is between hidden layers. Test them in a
world with autofeed 4, ball energy 1000, world size 50. Insecty's ability
to arient toward a food stimulus is incredibly precise. More creatures
coming soon.
Cheers,
Pete
BrainyFrog
(LAFFMMMX[0:0,1:0,2:-1.022,
3:0,4:-2.963,5:-354.869][-1:0.719,0:0,1:552.730,2:0,3:0.774,4:0][-2:3.427,-1
:0,0:0,1:0,2:0,3:0][0:0,1:3.403,2:0,-1:-1.995,-2:-586.205,-3:0,3:0,4:0,5:0,8
:-2.921,9:685.837,10:0,13:0,14:0,15:0,18:1.852,19:-3.066,20:0,23:1.653,24:0,
25:0][-1:-1.830,0:0,1:2.422,-2:-1.107,-3:0,-4:-1.211,2:0,3:0,4:-0.560,7:0,8:
0,9:0,12:-1.638,13:0,14:0,17:0,18:0,19:0,22:0,23:2.229,24:-1.394][-2:0,-1:0,
0:-134.204,-3:0,-4:1.938,-5:0,1:1.223,2:0,3:0,6:0,7:0,8:0,11:0,12:2.967,13:0
,16:-3.445,17:-1.552,18:-3.450,21:0,22:0,23:2.863][G:-831.992][S:0][T:0][@-4
:1.553,-5:-2.018,-6:0][| -5:-2.543,-6:-3.502,-7:-1.137],AMX[G:0][S:-2.332][T
:-0.670][@-9:-1.100,-10:-3.030,-11:0][| -10:0,-11:0,-12:0],AAIIX[G:0][S:-1.0
55][T:0][@-14:-1.472,-15:0,-16:-724.738][|-15:0,-16:0,-17:0],AMX[G:0][S:0][T
:0][|-21:3.925,-22:-3.903,-23:1.043][@-22:1.912,-23:0,-24:0],LAFFMMMX[G:0][S
:0][T:0][|-26:3.502,-27:0,-28:0][@ -27:0,-28:0,-29:-1.234])
Insecty
(RRlccccccMMX[4:0,5:0,6:0,7:0][3:0,4:-2.852,5:0,6:0][2:0,3:-782.054,4:0,5:0.
999][1:0,2:0,3:0,4:-2.766][-1:0,-2:0,-3:0,-4:0,4:0,6:0,8:0,9:0,11:-885.893,1
3:347.857,14:0,16:0,18:0,19:0,21:845.772,23:0,24:0,26:81.279,28:0,29:0,31:0,
33:1.875][-2:0,-3:0,-4:0,-5:0,3:0,5:0,7:0,8:0,10:0,12:0,13:0,15:0,17:0,18:0,
20:0,22:0,23:0,25:0,27:0,28:-1.720,30:-3.623,32:-4.792][-3:0,-4:0,-5:0,-6:-5
67.669,2:0,4:-0.664,6:0,7:0,9:0,11:0,12:0,14:2.317,16:0,17:923.453,19:-1.383
,21:0,22:0,24:0,26:0.546,27:0,29:0,31:1.880][-4:0,-5:0,-6:0,-7:0,1:-0.988,3:
0,5:-4.507,6:1.882,8:0,10:4.635,11:0,13:0,15:0,16:0,18:-0.952,20:0,21:-927.9
04,23:0,25:0,26:-1.335,28:0,30:-2.792][G:-2.551][|-5:0,-4:0,-3:0,-2:0]lMMX[S
:0][|-7:0,-6:0,-5:0,-4:0][T:0],MMIIIIIX(RRlccccccMMX[G:0][|-10:0,-9:1.753,-8
:0,-7:2.147]lMMX[S:-1.963][|-12:0,-11:0,-10:0,-9:0.372][T:0],MMIIIIIX(RRlccc
cccMMIIX[G:-4.977][|-15:0,-14:0,-13:0,-12:0][S:0]lMMX[|-17:0,-16:0,-15:0.453
,-14:4.457][T:0],,RRlccccccMMIIX[G:0][|-20:-0.794,-19:0,-18:0,-17:365.418][S
:-1.791]lMMX[|-22:0,-21:0,-20:0,-19:0][T:0]),RRlccccccMMX[G:2.914][|-25:-152
.862,-24:0,-23:0,-22:-300.907]lMMX[S:441.636][|-27:1.137,-26:0,-25:0,-24:-2.
410][T:2.587]),RRlccccccMMX[G:0][|-30:0,-29:0,-28:0,-27:-1.726]lMMX[S:-1.086
][|-32:0,-31:0,-30:0,-29:0][T:0])
--
___________________________________________
P E T E M A N D I K
Assistant Professor and
Associate Director, Cognitive Science Laboratory
Department of Philosophy
William Paterson University of New Jersey
265 Atrium Building
300 Pompton Road
Wayne, NJ 07470
(973)-720-2173
mandikp@wpunj.edu
http://www.wpunj.edu/cohss/philosophy/faculty/mandik