-
hi, im trying to create a DqnAgent agent with a mask for valid/invalid actions, according to [this post][1]
, i should specify a ```splitter_fn``` for the ```observation_and_action_constraint_splitte…
-
Hello,
Thanks for a great project. It's very useful. I have a question on the model code related to the Dueling algorithm. For example:
**Pong-v0_DQN_CNN_TF2.py**
Here is an example of the code:
…
-
### What happened + What you expected to happen
### Description
I was trying to save the SlateQ Policy so I could Serve it. The save worked. But restore did not. Trying to restore the trained S…
-
Hi,
I think there is a mistake in the quantile regression loss definition at slide 29 (lecture 5).
The indicator should be the other way around.
$L(\hat{x}) = \mathbb{E}_{x \sim P} \left[ (\hat{…
-
## 3、gazebo 关闭 client 界面
在做强化学习训练时,打开 gazebo 界面可能会使训练比较耗时,因此关闭 client 界面也许是一种比较好的方法。
gazebo 平台第三视角关闭方法如下:
```
$ roscd gazebo_ros
$ cd launch
$ sudo gedit empty_world.launch
```
在打开的文件中…
-
Some management boards couldn't boot into user space.
We saw three phenomena:
1. DDR failures
2. Unstable system boot-up
3. Watchdog timeout
We provided DDR Sweep testing on a failure board w…
-
The quick start code provided in the README is producing an error. Could you please review the code and error message below
```from boptestGymEnv import BoptestGymEnv, NormalizedObservationWrapper,…
-
Let's revision Bolts and breathe some fresh air into them! As outlined in #819 and on a Slack channel, we will revisit every single feature within Bolts.
Please sign up for a feature which you'd li…
-
Hi, I am the developer of [DI-engine](https://github.com/opendilab/DI-engine), we are developing a new DRL platform with [various algorithms](https://github.com/opendilab/DI-engine#algorithm-versatili…
-
Thank you for your instructions. I can run your models.
but I have some questions. I am very happy with your reply
1) You mentioned that this model is applied for an isolated intersection in your…