Closed jiakai0419 closed 6 years ago
Fixed in https://github.com/ikostrikov/pytorch-a3c/commit/e898f7514a03de73a2bf01e7b0f17a6f93963389
Also there are some warnings that do not affect performance of the algorithm.
I will fix them closer to the 0.5.0 release.
Your efficient response touched me.
@ikostrikov I think the performance is affected in version 0.4.0
python3 main.py --env-name "PongDeterministic-v4" --num-processes 16
Time 00h 00m 09s, num steps 5031, FPS 519, episode reward -21.0, episode length 812
Time 00h 01m 10s, num steps 35482, FPS 501, episode reward -2.0, episode length 100
Time 00h 02m 11s, num steps 66664, FPS 505, episode reward -2.0, episode length 100
Time 00h 03m 13s, num steps 97058, FPS 503, episode reward -2.0, episode length 100
Time 00h 04m 14s, num steps 128517, FPS 504, episode reward -2.0, episode length 108
Time 00h 05m 24s, num steps 163141, FPS 502, episode reward -21.0, episode length 764
Time 00h 06m 34s, num steps 200426, FPS 508, episode reward -21.0, episode length 764
Time 00h 07m 57s, num steps 245725, FPS 514, episode reward -21.0, episode length 1942
Time 00h 09m 16s, num steps 284730, FPS 511, episode reward -21.0, episode length 1324
Time 00h 10m 41s, num steps 325153, FPS 507, episode reward -21.0, episode length 1324
Time 00h 12m 01s, num steps 361563, FPS 501, episode reward -21.0, episode length 1324
Time 00h 13m 28s, num steps 406910, FPS 503, episode reward -21.0, episode length 1964
Time 00h 14m 53s, num steps 450836, FPS 505, episode reward -21.0, episode length 1964
Time 00h 16m 22s, num steps 493876, FPS 503, episode reward -21.0, episode length 1964
How many cores do you have on your machine?
Is seems to start learning something since the length of the episodes goes up.
Number of Processors: 1
Total Number of Cores: 2
I will test that on 64 cores machine.
On 2 core machine it will just take a lot of time. I would expect a decent reward after 1h of training on Pong.
I'm using pytorch-cpu 0.4.1 and Python3.7 in Windows7.
Still see this error "TypeError: multinomial() missing 1 required positional arguments: "num_samples""
@ph-dev-2016 Try with the most recent version of this repository.
macOS 10.13.4 Python 3.6.4 pytorch 0.4.0
I encountered an error
I try to fix it
TypeError: multinomial() missing 1 required positional arguments: "num_samples"
I encountered a new error
I am very confused and cannot fix it.
TypeError: addcdiv_() takes 2 positional arguments but 3 were given