-
使用qmix_high_sample_efficiency.yaml情况下在较难的corridor地图下,test_battle_won_mean一直为0(实际上qmix.yaml也一样)。请教下那个地方可能出了问题,附上了完整的输出文件。
另外还有个比较随机的问题,某几次实验室的时候,会出现action不合法导致的assertion错误,导致程序直接退出(如下面的cout所示),不知道这个…
-
I debug it by pycharm, and I put the parameters "--config=qmix --env-config=sc2 with env_args.map_name=2s3z save_model=True save_model_interval=20000" in Edit Configurations.
there is:
FileNotFoundE…
-
Awesome work for extending the original pymarl! But will be much better if MPE can be included.
Is there any plan to open source the MPE-related code in this repository?
-
Awesome work! Just having trouble running MAPPO on the RWARE environment. My `run.json` is below. The main error is the `nan` causing `ValueError` appearing in the middle of training. I am wondering i…
-
How to implement joint-learning-based MARL algorithms(e.g. MAPPO, QMIX, etc.) but not independent-learning-based algorithms(such as ppo implemented in the paper) on warp-drive? Dow you have the plan t…
-
I am reading about the WQMIX, but I am not sure about the proof in the appendix:
![image](https://user-images.githubusercontent.com/18642955/109110370-f4fa8280-7771-11eb-90b2-7e5880a76981.png)
Why…
-
After running the command, I get the following file, but I don't see any files about tensorboard, how do I get the Episodic return graph?
![1](https://user-images.githubusercontent.com/105548396/2276…
-
Does anyone have code that reproduces the QMIX paper's graphs given the JSON files resulting from training?
-
首先非常感谢作者的代码分享。
第一点:COMA算法在运行8m_vs_9m时也遇到了NAN的问题,如下:
ValueError: Expected parameter probs (Tensor of shape (107520, 15)) of distribution Categorical(probs: torch.Size([107520, 15])) to satisfy the co…
-
We didn't build the Dockerfile and directly set up StarCraft II and SMAC by using bash install_sc2.sh. The environment we download includes StartCraftII folder and SMAC_Maps folder.
When we run "pyth…