-
I ran the example atari-dqn-dist.yaml example with the nightly image, following is the err log.
[err.log](https://github.com/opendilab/DI-engine/files/10242072/err.log)
I do not know the reason.
-
### 🚀 Feature
A clear and concise description of the feature proposal.
At present the `predict` method in the `BasePolicy` class contains quite a lot of logic that could be reused to provide sim…
-
In order to serve the policy in our serving infrastructure, which only supports ONNX/TF, I'm trying to export the policy in ONNX with [torch.onnx.export()](https://pytorch.org/docs/stable/onnx.html#fu…
-
### 🐛 Bug
When I train my model with a normal Monitor wrapped env I get the output tensorboard files as expected, but when I use a SubprocVecEnv with multiple parallel environments nothing seems to…
-
### 🐛 Bug
`policy` argument of `BaseAlgorithm` and `OffPolicyAlgorithm` has the type `Type[BasePolicy]` when it should be `Union[str, Type[BasePolicy]]`.
https://github.com/DLR-RM/stable-baselines…
-
Torch version: '1.11.0+cu113'
D3rlpy version: 0.90
I follow the tutorials of save and load. When I try to save a trained dqn policy into a onnx format. It has an error like this.
dqn.save_policy…
-
Hi, thanks for the great paper and sharing your code!
I really liked your paper and currently trying to re-implement it in pytorch / deep graph library (https://www.dgl.ai/). I would be grateful i…
-
Goal:
We want to provide an initial subset of control environments, which can be used during the development process. This includes environments from this [sheet](https://docs.google.com/spreadsheets…
-
Although current training speed is not bad it takes almost a month(2,685,280s) to train IQN for 200M frames in atari environment, So if separating training part and worker parallelly as mentioned on t…
-
Details
## Problem Description
Pytorch DQN fails on MountainCar. Try two settings in [the issue](https://github.com/vwxyzjn/cleanrl/issues/156)
## Checklist
- [x] I have installe…