-
Hello,
I have some trouble understanding UnVecWrapper. When training with SAC, using the scripts provided in [Stable Baselines Zoo](https://github.com/araffin/rl-baselines-zoo)
```bash
python t…
-
Hello. My objective is to imitate an expert using GAIL. I train a gym env with an RL algo (say TRPO), generate expert data from the learned model (using [``generate_expert_traj``](https://stable-basel…
-
## Issue description
Presently, under Julia 1.0.1, PyPlot's PyCall module fails to compile with the error:
```julia
julia> Pkg.build("PyCall")
Building Conda ─→ `~/.julia/packages/Conda/uQitS/…
-
Hi all,
Can't get the same results twice with TD3 but it works with PPO2.
```python
import gym
from stable_baselines import TD3
from stable_baselines.td3.policies import MlpPolicy
env = gy…
-
I'm training an agent on a custom environment using SAC. The environment is wrapped in a `Monitor`, which is wrapped in a `DummyVecEnv`, which is wrapped in a `VecNormalize`, with `norm_reward = True`…
-
This is possibly quite trivial, but the `evn.render()` lines of the code examples do not run for multiprocess environments unless unless `n_envs=1` in `make_vec_env()`.
For example, the code exampl…
-
doesn't work...
-
I am trying to save the GAIL model during training. I'm using the example code from the [Callback](https://stable-baselines.readthedocs.io/en/master/guide/callbacks.html#checkpointcallback) documentat…
-
I have tried Pendulum-v0 animation to run in different codes but the code of stable_baselines docs of SAC only shows me the first frame of pendulum render screen and does not animate throughout.
He…
-
Hi!
Currently the reward function for pendulum-v0 is:
`-(theta^2 + 0.1*theta_dt^2 + 0.001*action^2)`
The signs of theta, theta_dt and action are not considered. If the angle < 0 and torque > 0 …