Difference between revisions of "Thread:Talk:ScalarBot/Version History/how to build a good test bed?/reply (6)"

From Robowiki
Jump to navigation Jump to search
 
m
 
Line 3: Line 3:
 
For movement, often a single bot is enough to prove a theory. Escape angle tuning is a rambot plus DevilFish, surfing mechanics is DoctorBob, anti-GF RaikoMicro, anti-fast-learning is Ascendant and for general unpredictability Shadow or Diamond.
 
For movement, often a single bot is enough to prove a theory. Escape angle tuning is a rambot plus DevilFish, surfing mechanics is DoctorBob, anti-GF RaikoMicro, anti-fast-learning is Ascendant and for general unpredictability Shadow or Diamond.
  
Targeting I always find less interesting. Maybe because it is a more pure ML problem, with less ways to optimise that haven't already been studies in a related field. I decided to brute-force it by adding lots of features and then using a genetic optimization to tune the weights. The surfers I did separately, but with the same process.
+
Targeting I always find less interesting. Maybe because it is a more pure ML problem, with less ways to optimise that haven't already been studied in a related field. I decided to brute-force it by adding lots of features and then using a genetic optimization to tune the weights against recordings of the entire rumble population, about 5000 battles. The surfers I did separately, but with the same process.

Latest revision as of 22:15, 27 September 2017

It depends what I am working in.

For movement, often a single bot is enough to prove a theory. Escape angle tuning is a rambot plus DevilFish, surfing mechanics is DoctorBob, anti-GF RaikoMicro, anti-fast-learning is Ascendant and for general unpredictability Shadow or Diamond.

Targeting I always find less interesting. Maybe because it is a more pure ML problem, with less ways to optimise that haven't already been studied in a related field. I decided to brute-force it by adding lots of features and then using a genetic optimization to tune the weights against recordings of the entire rumble population, about 5000 battles. The surfers I did separately, but with the same process.