Difference between revisions of "User:Darkcanuck"

From Robowiki
Jump to navigation Jump to search
m (added Holden)
m (→‎Bots: added B26354)
 
Line 19: Line 19:
 
* [[Pris]] - 1on1 bot using reinforcement learning for movement and Gaff's neural targeting.
 
* [[Pris]] - 1on1 bot using reinforcement learning for movement and Gaff's neural targeting.
 
* [[Holden]] - 1on1 [[Wave Surfing]] bot with Gaff's neural targeting.
 
* [[Holden]] - 1on1 [[Wave Surfing]] bot with Gaff's neural targeting.
 +
* [[B26354]] - Melee bot derived from Holden + Gaff with some minimum risk movement thrown in.

Latest revision as of 06:30, 11 September 2009


About the Canuck

Darkcanuck is Jerome Lavigne, a mid-thirties consulting engineer living in Vancouver BC (Canada). I'm not a hardcore programmer but I do specialize in manufacturing automation and control systems, which rely heavily on software. I'm fascinated by robots, whether real or virtual.


Projects


Bots

I'm interested in AI techniques which focus on learning and adaptation rather than creating bots based on statistical methods. We'll see how that works out.

  • Leon - Melee bot using a neural network for targeting, reinforcement learning for movement.
  • Gaff - 1on1 bot with a simple movement strategy and an array of neural nets for GF-style targeting.
  • Pris - 1on1 bot using reinforcement learning for movement and Gaff's neural targeting.
  • Holden - 1on1 Wave Surfing bot with Gaff's neural targeting.
  • B26354 - Melee bot derived from Holden + Gaff with some minimum risk movement thrown in.