DeepHoldem icon indicating copy to clipboard operation
DeepHoldem copied to clipboard

Published 20 hours ago • verified publisher icon happypepper

Samples count

Open snarb opened this issue 6 years ago • 3 comments

Hi! How much samples did you use to train the network? What was the huber loss? Can You share the training data to play with it and compare with my? (I have implimented deepStack in c++ now generating samples)

snarb avatar Jun 04 '18 06:06 snarb

I've added the training details to the readme. You can also observe the validation losses yourself by going to Data/Models/NoLimit/<street> and th, then torch.load('final_cpu.info') in the interactive terminal.

happypepper avatar Jun 04 '18 20:06 happypepper

Thanks. Didn't you measure the loss after the buckets CFR ->hole hands CFR conversion, not for the buckets? Bucketing by itself should add extra loss. It is interesting how much.

snarb avatar Jun 04 '18 21:06 snarb

Actually, the loss was measured after the hole -> buckets conversion, so I think the real loss will be higher than the reported loss (but I'm not sure). I agree it would be interesting to measure the difference.

happypepper avatar Jun 04 '18 23:06 happypepper