-
Hello, I encountered the following error while running dqn.py. It seems that the error is due to the state s not being correctly initialized as a valid sequence containing four elements. I attempted …
-
I am trying to build Open Spiel for the first time. Using a new Ubuntu 22.04 install under WSL2. I am building with Cuda and libtorch. After a bunch of tinkering, I have gotten down to everything bu…
-
Hi Guy,
I tried your code, that is rare code I can run with such a simple environment configuration!
I can run using your code. But I tried to changed a little in order to support M1 GPU, but it…
-
### What is the problem?
It seems to be that when using Apex DQN in combination with the config parameter "use_exec_api=True", Apex DQN only gathers the batches of 1 worker instead of all workers.
I…
-
https://nkucs.icu/#/courses/grade-2/COSC0015
NKUCS，一个充满了「神仙」和「神仙」课程的专业，本网站旨在记录 NKUCS 的信息以及历届学生的评价
-
`wandb --version && python --version && uname`
wandb, version 0.9.1
Python 3.7.4
Linux
### Description
There are two issues with the current support for gym logging.
**1) Inconsistent slid…
-
### What is the problem?
DQNTrainer with TORCH framework fails when attempting to perform operations between tensors of different dtypes. I think there are multiple places tensors should cast to…
-
您好，出现这个错误是因为当前版本没考虑到Windows系统下，magent2环境的动态链接库文件。您可以试着安装一下这个环境，再看是否还会出现该错误？
`pip install magent2`
我们后期会修补这个问题，感谢您的反馈!
_Originally posted by @wenzhangliu in https://github.com/agi-br…
-
docker运行的是**ding:nightly**版本，docker pull opendilab/ding:nightly。
运行使用 DQN 算法训练的智能体模型： [final.pth.tar](https://opendilab.net/download/DI-engine-docs/01_quickstart/final.pth.tar)
报错如下：
.to(self.q_eval.device)
```
Instead of:
```
loss = self.q_eval.loss(q_target, q_pr…
i1Cps updated
8 months ago