-
When running an experiment with Docker (`bash run.sh $GPU python3 src/main.py --config=qmix_smac --env-config=sc2 with env_args.map_name=2s3z`) I get the following issue:
`standard_init_linux.go:207:…
-
Hi, thank you for your amazing contribution! I'm doing some research based on qmix which may include parallel and episode runner at the same training stage. But I got reward around 18 when test_battle…
qyz55 updated
4 years ago
-
When executing the following command, according to the installation instructions
```
bash run.sh $GPU python3 src/main.py --config=qmix --env-config=sc2 with env_args.map_name=2s3z
```
I obtai…
-
Hello
I want to run RODE in parallel
However, looking at the code, the parallel execution side is not able to respond.
Is it impossible to run in parallel?
-
Hello,
First, I run this code and it seems go well(Cause I get "INFO:root:step:20000/20000, action:7, reward:-0.0")
`python run_rl_control.py --algo DuelDQN --inference --num_step 20000 --ckpt mod…
-
Thank you for sharing, I meet some problems, and hope you can solve my doubts.
**Question 1: Bugs**
It seems that the code cannot run successfully, I encountered the following bug:
When I run
…
-
In very much the same vein as [this MADDPG issue](https://github.com/PettingZoo-Team/PettingZoo/issues/182), I was wondering if there are examples of using QMIX on PettingZoo environments. For QMIX, t…
-
麻烦您请教一下，在多agent 的情况下，最终目的是为了得到多个相同结构的网络？但是这要怎么训练呢，因为这并不是分布式数据平行只为了最终得到一个网络，
我的数据必须由两个进程各自提供，然后还有一个上层网络，上面网络的loss应该要会给各自两个网络，但是他们跨进程，不知道怎么能把梯度跨进程传递，其实就是Qmix下面带网络，网络结构一样但是位于不同的进程谢谢
-
when i run this command "sudo python3 src/main.py --config=qmix_smac --env-config=sc2 with env_args.map_name=2s3z". it can produce some files in results. But it can't run completely.Some errers come …
-
Is there a way I can use your QMIX implementation to train a model on a different environment? For simplicity assume the generic `env` variable has the same functions/attributes, etc as SMAC. I'm more…