stable-baselines3

Stable Baselines3 (SB3) is a PyTorch-based library providing reliable implementations of reinforcement learning algorithms. This skill provides comprehensive guidance for training RL agents, creating custom environments, implementing callbacks, and optimizing training workflows using SB3's unified API. Basic Training Pattern: Important Notes: Algorithm Selection: Use references/algorithms.md for detailed algorithm characteristics and selection guidance. Quick reference: See scripts/train_rl_agent.py for a complete training template with best practices. Requirements: Custom environments must inherit from gymnasium.Env and implement: Key Constraints: Validation: See scripts/custom_env_template.py for a complete custom environment template and references/custom_environments.md for comprehensive guidance. Purpose: Vectorized environments run multiple environment instances in parallel, accelerating training and enabling certain wrappers (frame-stacking, normalization). Types: Quick Setup: Off-Policy Optimization: When using multiple environments with off-policy algorithms (SAC, TD3, DQN), set gradient_steps=-1 to perform one gradient update per environment step, balancing wall-clock time and sample efficiency. API Differences: See references/vectorized_envs.md for detailed information on wrappers and advanced usage.