Closed zmonoid closed 4 years ago
Is my understanding correct?
Yes, your understanding is correct. Essentially, the reported time is the average time for running the train_dqn.py
script from start to finish (roughly speaking) on a single GPU. There's 200M emulator frames, but 50M timesteps/actions from the agent. So essentially 160 actions per sec (excluding periodic evaluations).
I'll try and inquire more about the compute requirements used for these results.
As for the hardware, we used a single NVIDIA V100 with 1 Intel Xeon CPU clocked @ 3GHz and 12GB of RAM.
@ummavi @prabhatnagarajan Really thanks for your explaination.
May I know the training speed for a single trial?
In your reproduction section, e.g. DQN:
Does this mean that, the training for a single trial is:
200,000,000 frames / (3.613 24 3600 sec) = 640 frames/sec
Above calculation is inline with Deepmind. With default frame skip = 4, the actual speed is:
50,000,000 frames (collected) / (3.613 24 3600 sec) = 160 frames/sec
Is my understanding correct?
Also, may I know your hardware?