hmp2g
hmp2g copied to clipboard
Multiagent Reinforcement Learning Research Project
It seems impossible for me to download the docker image fuqingxu/hmp:latest with docker-ce......I succeeded with docker-desktop, but the NVIDIA container toolkit seems not supporting docker-desktop. The docker pulling process would...
I am developing a multi-agent reinforcement learning environment based your framework, and I want to deploy your docker image on WSL. However, when I enable the --gpus all option, I...
AssertionError: ('cannot find', 'MISSION/collective_assault') I want to run DCA related experiments, but the above problem occurred. Do I need to write the missing file myself? Or could you provide the...
I am using GPU to run this program, but the GPU usage is very low. How can I increase the GPU usage to make the program execute faster? What settings...
Traceback (most recent call last): File "D:\Program Files\JetBrains\PyCharm Community Edition 2019.3.5\plugins\python-ce\helpers\pydev\pydevd.py", line 1434, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "D:\Program Files\JetBrains\PyCharm Community Edition 2019.3.5\plugins\python-ce\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18,...
when I set up the docker environment, I run the command `$ docker run -itd --name hmp-$USER \ --net host \ --gpus all \ --shm-size=16G \ fuqingxu/hmp:latest` It's download speed...
 I have successfully installed docker, and when I run [git pull && python main.py -c RESULT/50RL-55opp/test-50RL-55opp.jsonc] in the container, I get the error in the image
Is ppo_ma here means IPPO but not MAPPO since actor and critic share a common part and the feature_dim of input is the same?
1. After all the procedures, render_result.jsonc was executed.  (hmp_env) PS C:\Users\user\Documents\GitHub\hmp2g_01> python main.py -c RESULT/uhmap_hete10vs10/render_result.jsonc 2. There's a problem  Port 55578 will be used by hmp, port 55579...
File "/home/nkw/code/hmp2g-master/ALGORITHM/common/hyper_net.py", line 49, in forward hidden = F.relu(torch.matmul(x_, w1) + b1) # b * t, 1, emb RuntimeError: Expected size for first two dimensions of batch2 tensor to be:...