-
Hi,
Playing around with stable baselines 2.9.0 (installed with pip) on Ubuntu 18.04.4 LTS with Python 3.6.9, gym 0.16.0, tensorflow 1.14.0 and pybullet 2.6.5.
When I run
```
python enjoy.py -…
-
I'd like to implement Hindsight Experience Replay (HER). This can be based on a whatever goal-parameterized RL off-policy algorithm.
**Goal-parameterized architectures**: it requires a variable for…
-
With @hill-a , we came up to the same conclusion about things in the common folder: a lot is not specific to this library and could be separated in a stand-alone python package.
Doing so would:
- …
-
**Describe the bug**
The current default value form `hyperparams` raises an **AttributeError** in [`utils.create_test_env`](https://github.com/araffin/rl-baselines-zoo/blob/da52f568282de8e3b0a7435eb6…
-
I noticed that some time ago, exactly at Nov 21, 2019, there was a change in documentation by @AdamGleave
The change in file `docs/guide/install.rst` was from line:
`docker pull araffin/stable-base…
-
Hello,
I trained the ARS (from the paper here: https://arxiv.org/pdf/1803.07055.pdf) on the Half-Cheetah and Ant environments. It works very well with Mujoco but not with PyBullet. In PyBullet the …
-
Hi
I do not know if you might consider this as a question that I can ask you. I have been working with a PPO agent code that seemed to train for the environment (custom) that I have. However, in or…
-
According to the docs, when creating custom environments, we should always normalize the observation space. For this, you have the VecNormalize wrapper, which creates a moving average and then normali…
-
I understand that there is a way to tune hyperparameter. Is there a way to tune the actual model (number of layers and tensors) to speed-up training?
If not, is it possible to integrate something lik…
-
I tried run the trained agents locally and from Docker, the same bug about FlattenDictWrapper appear
**Code example**
```
Traceback (most recent call last):
File "train.py", line 25, in
…