search

shariqiqbal2810 / MAAC

Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019
MIT License
666 stars 172 forks source link

Memory Leak #31

Closed yuchen-x closed 3 years ago

yuchen-x commented 3 years ago

Hi,

When I run the code under the fullobs_collect_treasure domain on cpu only, I noticed there was memory leak happening inside of model.update_critic and model.update_policies functions. Even though the buffer is fully filled, the memory usage will keep going up and finally use out of my memory. I don't know which line of the code leads to this problem.

Does anyone run into this issue? Thank you!

yuchen-x commented 3 years ago

I added LSTM into policy net which causes the memory leak on CPU-only training case.

Refer to the issue ticket