-
Currently I have to modify the print function in setup.py to install, I haven' t tested whether it can be used with python 3. Is there python 3 support for now?
-
Hi,
I try to train some new game, but I got Segmentation fault, e.g.
$ ./train.sh roms/STAMPEDE.BIN
A.L.E: Arcade Learning Environment (version 0.5.1)
[Powered by Stella]
Use -help for help screen.…
-
Two problems I got when I following you PostII . I am not sure where the problem is. Sincerely Thank you for answer~ ！
When I run the python virtual environment , I got a problem of h5py version is 1…
-
The default random number generator of numpy seems to be used throughout the code (`grep np.random`). For example in: [mountain_car.py](https://github.com/openai/gym/blob/master/gym/envs/classic_contr…
-
For more information, I will refer readers to [this blog post](http://blog.puppylinux.com/?viewDetailed=00025).
I have created 2 new branches `legacy` and `rationalisation`.
### Important
As @mrfri…
-
I'm trying to run 16 ALE_python_interface instances in parallel and run the games simultaneously using concurrent.futures.ProcessPoolExecutor.map
However, I got stuck when calling ale.act(action) in …
-
This is the output when starting to train the model, it tells me that Device 0 does not have CUDA compute capability 5.0 or greater, however I am running CUDA 7.0 with GTX750TI, I can run the Caffe m…
-
Hey guys,
I'm not sure if it's supposed to be like this, but using ale_python_inferface's getScreenGrayscale I get the following image in breakout. You can see that the paddle is averaged out from it…
-
I'm trying to train a network on pong using a variant of [Nathan Sprague's deep_q_rl implementation](https://github.com/jcatw/deep_q_rl/tree/multiplayer). I should have cuda toolkit and cudnn installe…
-
Is your implementation of pyrlcade includes "pong.bin" is publicly available? Thanks!