run in gpu error
zdx3578 opened this issue · 3 comments
Fitting imagination rollout model...
Done fitting, 200 timesteps covered.
Performing imagination rollout for 5 steps
Traceback (most recent call last):
File "naf_ir.py", line 255, in
postobs, rewards, terminals = ir_model.predict(preobs, actions, timesteps + i)
File "/home/ubuntu/gymexperiments/irmodel.py", line 107, in predict
postob = np.random.multivariate_normal(obsmeans, obscov)
File "mtrand.pyx", line 4689, in mtrand.RandomState.multivariate_normal (numpy/random/mtrand/mtrand.c:32216)
ValueError: mean must be 1 dimensional
do you run this code in gpu?
before i am run it in cpu is ok! gpu server the theano is update to git latest version,maybe some lib conflict
pip sklearn is not update!
I barely got the imagination rollout code working, but haven't had time to put it through tests. Let me know if it works for you!
when pip update sklearn； running ok！ thanks very much！