Download Latest Version v2.8.0_ Dropped Python 3.9, added Python 3.13 support, MaskablePPO bug fix, default hyperparams for unlisted env in the RL Zoo, Markdown doc source code.tar.gz (1.4 MB)
Email in envelope

Get an email when there's a new version of Stable Baselines3

Home / v2.6.0
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2025-03-24 3.0 kB
0
v2.6.0_ New _LogEveryNTimesteps_ callback and _has_attr_ method, refactored hyperparameter optimization source code.tar.gz 2025-03-24 1.4 MB
1 1 weekly downloads
v2.6.0_ New _LogEveryNTimesteps_ callback and _has_attr_ method, refactored hyperparameter optimization source code.zip 2025-03-24 1.5 MB
1 1 weekly downloads
Totals: 3 Items   2.9 MB 2

SB3 Contrib (more algorithms): https://github.com/Stable-Baselines-Team/stable-baselines3-contrib RL Zoo3 (training framework): https://github.com/DLR-RM/rl-baselines3-zoo Stable-Baselines Jax (SBX): https://github.com/araffin/sbx

To upgrade:

pip install stable_baselines3 sb3_contrib rl_zoo3 --upgrade

New Features:

  • Added has_attr method for VecEnv to check if an attribute exists
  • Added LogEveryNTimesteps callback to dump logs every N timesteps (note: you need to pass log_interval=None to avoid any interference)
  • Added Gymnasium v1.1 support

Bug fixes:

  • SubProcVecEnv will now exit gracefully (without big traceback) when using KeyboardInterrupt

SB3-Contrib

  • Renamed _dump_logs() to dump_logs()
  • Fixed issues with SubprocVecEnv and MaskablePPO by using vec_env.has_attr() (pickling issues, mask function not present)

RL Zoo

  • Refactored hyperparameter optimization. The Optuna Journal storage backend is now supported (recommended default) and you can easily load tuned hyperparameter via the new --trial-id argument of train.py.
  • Save the exact command line used to launch a training
  • Added support for special vectorized env (e.g. Brax, IsaacSim) by allowing to override the VecEnv class use to instantiate the env in the ExperimentManager
  • Allow to disable auto-logging by passing --log-interval -2 (useful when logging things manually)
  • Added Gymnasium v1.1 support
  • Fixed use of old HF api in get_hf_trained_models()

SBX (SB3 + Jax)

  • Updated PPO to support net_arch, and additional fixes
  • Fixed entropy coeff wrongly logged for SAC and derivatives.
  • Fixed PPO predict() for env that were not normalized (action spaces with limits != [-1, 1])
  • PPO now logs the standard deviation

Deprecations:

  • algo._dump_logs() is deprecated in favor of algo.dump_logs() and will be removed in SB3 v2.7.0

Others:

  • Updated black from v24 to v25
  • Improved error messages when checking Box space equality (loading VecNormalize)
  • Updated test to reflect how set_wrapper_attr should be used now

Documentation:

  • Clarify the use of Gym wrappers with make_vec_env in the section on Vectorized Environments (@pstahlhofen)
  • Updated callback doc for EveryNTimesteps
  • Added doc on how to set env attributes via VecEnv calls
  • Added ONNX export example for MultiInputPolicy (@darkopetrovic)

New Contributors

Full Changelog: https://github.com/DLR-RM/stable-baselines3/compare/v2.5.0...v2.6.0

Source: README.md, updated 2025-03-24