search

rll / rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
Other
2.91k stars 801 forks source link

How to improve the GPU-Util when running RL program with RLLab. #252

Open morantumi opened 5 years ago

morantumi commented 5 years ago

Hi, I have tried my best to archieve this goal but i failed. I found that theano＝0.9.0　pygpu=0.6.5 and theano=1.0.2 pygpu=0.7.5 can pass the test program and the result is showed as follow. I think it can prove that theano can work correctly. image However, when I run python program in rllab with the setting use_gpu=True, I still have the bad result like following: image I think the config of theano is ok because the test program is running correctly. And ~/.theanorc is setted with device=cuda0. When I run program with setting use_gpu=False, everything is ok. So I think the problem is about the Theano with GPU. So I'm really confused and please tell me how to use thean with GPU to accelerate rllab. Thank you very much.

morantumi commented 5 years ago

I solve the problem. However, the GPU-Util is too low I use the command watch -n 0.1 nvidia-smi and find the GPU-Util is about 3%~5%. And most of time is 0%. I don't know how to deal with it. could you give me some advice?

qxtian commented 4 years ago

can you tell me the solution for the problem- "you are tring to use the old GPU back-end'? thanks.