Open babak-badnava opened 6 years ago
Hi, can you provide some more details? Are you using the basic version of the algorithm with Pong? Automatic scheduling enabled? How many agents / trainers / predictors? Is the number of agents / training / predictor growing during training or does it stabilize? Thanks
Hi, yes I do use the basic version with Breakout game and Dynamic setting is off and 32 agents running with 2 trainer threads and 2 predictor threads. all the settings are fixed during training but memory usage will growth. I think this may be because of tensorflow memory leak.
Tensor flow version?
tensorflow version 1.2.1 installing from binary cuda version 7.5
I have tested the code on GTX 1080 with 32g Ram but when I run the code memory usage increases over time and after about 30 hours it will take all 32g of ram and make system to dies