Overhead run #3

Revisiting this whole neural net thing. Did another, longer run after tweaking a bunch of things (mostly removing cruft from the side-view test, like jumping and "grounded" and such).
run length:28
01234567891011121314151617181920212223242526
avg0.11118350.11751510.11617130.12565720.13688070.1563310.16561640.20839510.26791690.37956520.49561230.65011810.5612270.7630230.6263450.6848750.91963410.75143650.88850591.0652710.96150930.8098810.7446751.0010240.8382290.89157540.8473446
max0.24504590.27551090.22391210.42355140.48726720.48368050.91547671.0488010.80019580.85897091.1265221.1067790.94524681.0103830.79434391.0487691.185260.94576761.1496091.2348391.2027670.98070281.0266311.0796510.87430930.93146660.9513353
Population Size
100
Run Length
20
Do Training
False
Do Hybrid Training
True
Do Competitive Run
False
Inputs
hasTarget,targetLeft,targetRight,targetNorth,targetSouth,dirToTarget,distToTarget,wall,sensor0,sensor1,sensor2
Outputs
left,right,up,down,run,sensordir0,sensordir1,sensordir2
Hidden Layers
8 12 12 8
Back Propogation
True
Learning rate
0.5
Momentum
0.1
Growth rate
0.5