-
I created a custom gym environment and successfully trained a model using PPO. I then saved it using the model.save() method and got back a zip file (as per the documentation [here](https://stable-bas…
-
My env:
* I've installed all the dependencies via pip. I've set `MUJOCO_GL=egl` and installed `egl`.
* My OS is Ubuntu22.04 x86_64.
* My python version is `3.9`.
* My cuda version is 12.3 (from `…
-
### 🚀 Feature
Support [optax optimizer schedules](https://optax.readthedocs.io/en/latest/api/optimizer_schedules.html) (as argument for `learning_rate`).
### Motivation
Learning rate scheduli…
-
### 🐛 Bug
When training SAC/PPO models with a custom environment, I consistently observe the model predicting the same action. Even when I set a large penalty in the environment to discourage repeate…
-
### 🐛 Bug
Can be fixed easily, see #1439
### To Reproduce
```python
env = gym.make("Pendulum-v1")
model = SAC("MlpPolicy", env, verbose=1)
model.policy = th.compile(model.policy) # Com…
-
During the use of Pearl, the consumption of VRAM keeps increasing continuously. Is there any w…
-
### 🐛 Bug
### To Reproduce
```python
import gymnasium as gym
from sbx import DDPG, DQN, PPO, SAC, TD3, TQC, DroQ
env = gym.make("Pendulum-v1")
model = TQC("MlpPolicy", env, verbose…
-
### 🐛 Bug
After training a PyBullet environment, I try to record a video of it:
`python -m rl_zoo3.record_video --algo sac --env Walker2DBulletEnv-v0 --exp-id 10 -f logs/ -n 100`
And I get the …
-
### 🐛 Describe the bug
When I install pytorch, then the `safety` SAC tool reports vulnerable packages on my system.
https://pypi.org/project/safety/
```console
pip3 install --pre torch torchvi…
-
您好，我用NoCNN，直接将深度图下采样后拉平，再和无人机状态量拼接，再送入全连接层得到动作输出，这样没问题，模型能学会避障和导航。
但是当我减少深度图的下采样倍数，导致拉平后特征维度太大，直接和状态量拼接会使得模型只关注深度图特征，从而只能学会避障而完全不会导航，见下图：
![env1_NoCNN_multiview2_smoothRD_swf3_18Wsteps gif_20230719_…