Open Xemnas0 opened 4 years ago
For reporting result I'm using Monitor wrapper from OpenAI: https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail/blob/master/a2c_ppo_acktr/envs.py#L51
It properly computes the number of original environment frames.
True, but I believe this is not taken into account in the print info while training, is it? FPS therefore should stand for number of environment steps per second, and not frames per second.
Yes, that's true. After the NeurIPS deadline I will change it to "env. steps per second" to avoid any potential confusion.
While training, the number of frames used so far is computer as
total_num_steps = (j + 1) * args.num_processes * args.num_steps
Shouldn't this be multiplied by the number of stacked frames (default 4)? Also, the number of updates would be
num_updates = int( args.num_env_steps) // args.num_steps // args.num_processes // frame_stack