-
### 🚀 Feature
Hi, since these days attention mechanisms and transformer architectures are everywhere, I thought that it would be good to have this also in SB3. I have found this implementation:
ht…
-
Hi @BinLiang-NLP ! In this [line](https://github.com/HITSZ-HLT/JointCL/blob/2b8a3e13c32cc81fcb2936451ff8a6f87382bc47/run_semeval.py#L529), the test set is used as the verification set to determine whi…
-
Hi,
I can not use the setting with stablebaselines because of the TensorFlow version issue. I tried to use the PPO in stable-baseline3 instead. However, both the reward and ewma reward are super un…
-
### âť“ Question
Hello,
I saw the previous post here https://github.com/DLR-RM/stable-baselines3/issues/543 with the corresponding paper and google collab notebooks. These helped for sure, thank y…
-
Run Stock_NeurIPS2018_2_Train.ipynb in FinRL/examples
Colab report error
t…
-
## Steps to Reproduce
1. Run `flutter create crash_test`.
2. Update ios/Runner/Info.plist files as follows:
```
CFBundleDevelopmentRegion
$(DEVELOPMENT_LANGUAGE)
CFBundl…
-
In the AnimalAI environment, when you want to take a step, the action has to be called as action.item(). This may be an issue with AnimalAI or it could be due to the way stable baselines stores the mo…
-
### 🚀 Feature
According to this [paper](https://arxiv.org/pdf/2006.05990), recomputing the advantage can be helpful for the PPO performance.
The function is provided by `tianshou` library.
http…
-
### 🚀 Feature
Hello Stable Baselines community,
I am currently working on state representation learning in Robotics, using an observation that consists of a latent vector obtained by encoding simu…
-
What environment is needed to run the code in scripts? Like gym and SB3?