stable-baselines3

stable-baselines3 copied to clipboard

[Feature Request] Inform what normalization from preprocess_obs was applied to verbose = 2

3

### 🚀 Feature I suggest we add a log with `verbose=2` that describe if preprocess_obs normalized any of the input for the network. ### Motivation This is a very small...

zippeurfou

Stuck when training with DDPG

2

### ❓ Question Hello, When I use DDPG to train the gym third party environment torcs (a racing environment), after a period of time when the program starts to run,...

betacatZ

[Question] The use of close() for remote in SubprocVecEnv

1

### ❓ Question Hi! I'm wondering about the close() in SubprocVecEnv. When initializing work_remote and remote, [stable-baselines3 code](https://github.com/DLR-RM/stable-baselines3/blob/68b190b667fe923889d234aa45864b2faaec651e/stable_baselines3/common/vec_env/subproc_vec_env.py#L108) uses close() for work_remote : ``` for work_remote, remote, env_fn in zip(self.work_remotes,...

dwyzzy

[Feature Request] Allow render in venv to return 4D array instead of tiling

2

### 🚀 Feature Support for not tiling images in vectorized environments and instead returning a 4-dimensional array. ### Motivation Untiling the image is fairly non-trivial (the tiling code is 10-15...

Rocamonde

Training exceeds total_timesteps

1

### ❓ Question Consider this setup: ```python import stable_baselines3 import gym from stable_baselines3 import DQN, A2C, PPO #from sb3_contrib import ARS, TRPO env = gym.make('MountainCar-v0') seed = 42 verbose =...

timosturm

[Question] DictRolloutBuffer seems very slow for larger observations

1

### ❓ Question I am using PPO with image observations. I profiled my training code today and noticed that a large part of the overall training time (second to the...

mlodel

Assert that the VecNormalize wrapper handles the new truncations correctly

2

> I need to think more about that one, but my guess is that it should not matter much, the scaling is meant to avoid large values and to evolve...

tlpss

SAC model not properly saved

5

### 🐛 Bug I'm training a SAC policy in a Mujoco's Humanoid environment for some iterations. After finishing training, I save the model, to resume training later. However, when restarting...

PabloVD

ValueError: could not broadcast input array from shape (23,) into shape (27,)

2

### 🐛 Bug Added more information to communicate the issue better. When I try gym.make and provide a custom xml_file with a different number of body parts to that of...

n-kish

Weights only param

1

## Description ## Motivation and Context - [ ] I have raised an issue to propose this change ([required](https://github.com/DLR-RM/stable-baselines3/blob/master/CONTRIBUTING.md) for new features and bug fixes) Relates to #1852 ## Types...

markscsmith