search

kyonofx / tia

[ICML 2021] Learning Task Informed Abstractions -- a representation learning approach for model-based RL in complex visual domains
https://xiangfu.co/tia
17 stars 3 forks source link

Runtime problem #1

Open yixiaoshenghua opened 2 years ago

yixiaoshenghua commented 2 years ago

Hi, I am very interested in your work "learning task informed abstractions" and want to reproduce the results shown in your paper. But when I set all the environments and run the code, I found it very slow to get the result. It takes several weeks but still does not return a result. My CPU is Intel i9-11900K and CPU is RTX 3060. I am confused whether this problem was caused by some missing settings or just caused by the device difference.

yixiaoshenghua commented 2 years ago

Running 10000 steps will take almost one week.

kyonofx commented 2 years ago

Hi, this is strange. For DMC it took me ~10 hours to run 1M steps on a single RTX 2080 Ti. Could you check your GPU utilization? My best guess is your GPU is not being properly used. This could be due to missing CUDA/Nvidia tools compatible with the Tensorflow version.