SB3 Contrib

We implement experimental features in a separate contrib repository: SB3-Contrib

This allows Stable-Baselines3 (SB3) to maintain a stable and compact core, while still providing the latest features, like Truncated Quantile Critics (TQC) or Quantile Regression DQN (QR-DQN).

Why create this repository?

Over the span of stable-baselines and stable-baselines3, the community has been eager to contribute in form of better logging utilities, environment wrappers, extended support (e.g. different action spaces) and learning algorithms.

However sometimes these utilities were too niche to be considered for stable-baselines or proved to be too difficult to integrate well into the existing code without creating a mess. sb3-contrib aims to fix this by not requiring the neatest code integration with existing code and not setting limits on what is too niche: almost everything remotely useful goes! We hope this allows us to provide reliable implementations following stable-baselines usual standards (consistent style, documentation, etc) beyond the relatively small scope of utilities in the main repository.


See documentation for the full list of included features.

RL Algorithms:

Gym Wrappers:


Documentation is available online:


To install Stable-Baselines3 contrib with pip, execute:

pip install sb3-contrib

We recommend to use the master version of Stable Baselines3 and SB3-Contrib.

To install Stable Baselines3 master version:

pip install git+

To install Stable Baselines3 contrib master version:

pip install git+


SB3-Contrib follows the SB3 API and folder structure. So, if you are familiar with SB3, using SB3-Contrib should be easy too.

Here is an example of training a Quantile Regression DQN (QR-DQN) agent on the CartPole environment.

from sb3_contrib import QRDQN

policy_kwargs = dict(n_quantiles=50)
model = QRDQN("MlpPolicy", "CartPole-v1", policy_kwargs=policy_kwargs, verbose=1)
model.learn(total_timesteps=10000, log_interval=4)"qrdqn_cartpole")