off-policy

off-policy copied to clipboard

Traceback (most recent call last): File "train_mpe.py", line 157, in main(sys.argv[1:]) File "train_mpe.py", line 147, in main total_num_steps = runner.run() File "D:\off-policy-release\offpolicy\runner\mlp\base_runner.py", line 153, in run env_info = self.collecter(explore=True, training_episode=True,...

b762927

环境可视化问题

2

请问我运行项目以后只能得到weight&biass平台的数据指标，但不能把simple_XXX.py环境渲染出来是为什么啊？

Solister00

Some questions about the code

1

why did the code require only one env when using rnn policy? https://github.com/marlbenchmark/off-policy/blob/release/offpolicy/scripts/train/train_mpe.py#L154

rainbow979

need a help

2

Hello, I have encountered some problems. I wonder if you can help me. that:Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment...

zhouweiqing-star

Bug with idx_range, causing error with Prioritized ER

3

**Describe the bug** When using PER with QMIX, an issue arises with the idx_range returned by the insert function of RecPolicyBuffer: > line 267, in insert for idx in range(idx_range[0],...

Maxtoq

Hello, Thanks for open-sourcing a really good work. I was wondering if you guys can open-source the MASAC code base as it would help to understand the variations of MASAC...

kailashg26

Run time

1

How much time is usually needed when running on mpe by Qmix?

Bruce-Lan-ZY

in mqmix mixer self.hyper_b2 = nn.Sequential( init_(nn.Linear(self.cent_obs_dim, self.hypernet_hidden_dim)), nn.ReLU(), init_(nn.Linear(self.hypernet_hidden_dim, 1)) ).to(self.device) should be self.hyper_b2 = nn.Sequential( init_(nn.Linear(self.cent_obs_dim, self.mixer_hidden_dim)), nn.ReLU(), init_(nn.Linear(self.mixer_hidden_dim, 1)) ).to(self.device) ?

zcyyyyyyyyyyy

As I work with this code, I find that what wandb records is somewhat different from what I intuitively expect. When I try to train mqmix with MPE environment, in...

lilyleii

jason-huang03