Dami Choi
Dami Choi
Sorry, why is it an invalid CoinIndexedVector in packed mode? When I print the dense vector, I get [-6, 6] with indices [2, 0].
I'm sorry for being slow, but could you please elaborate? My main confusion is that whether updates is packed or not, the final output should be the same, but it's...
Hi, I'm sorry for the late response. When we tuned for spanning tree, our learning rate range was [1e-4, 1e-2] (and temperature [1e-1, 1e1] which is what you already have)....
I'm glad it worked! For T=20 it should be easier to find a working set of hyperparameters. One of the trials that worked for us was: lr = 0.00019936764261965588 temp...
Hello, thanks for trying out our code! instead of " return wrap_deepmind(env)" in line 21 of run_atari.py can you try "return MaxAndSkipEnv(env)" and change the import statement to: "from baselines.common.atari_wrappers...
Was this problem ever resolved?
Sorry if I'm being stupid, but If I understand correctly, your computation of Binv uses getBInvACol, while the code in lp.basisInverse does getBInvCol. If I do: ``` import numpy as...