stable-baselines3
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
- Version
- 1.3
- License
- MIT license
- Compatibility
- Requires Python 3.10+, PyTorch >= 2.3, and stable-baselines3 2.8+. Gymnasium environments; optional extras for TensorBoard and Atari (ale-py).
Pinned to revision 70a605012eee, so it is the text this page describes rather than whatever the author pushed since.
Pre-approved tools experimental
Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.
- Read
- Write
- Edit
- Bash
Files
- skills/stable-baselines3/SKILL.md
- skills/stable-baselines3/references/algorithms.md
- skills/stable-baselines3/references/callbacks.md
- skills/stable-baselines3/references/custom_environments.md
- skills/stable-baselines3/references/vectorized_envs.md
- skills/stable-baselines3/scripts/custom_env_template.py
- skills/stable-baselines3/scripts/evaluate_agent.py
- skills/stable-baselines3/scripts/train_rl_agent.py
Every link opens the file at its source, pinned to the revision this page describes.