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.

提供生产就绪的强化学习算法（PPO、SAC、DQN、TD3、DDPG、A2C），采用类似 scikit-learn 的 API，适用于标准强化学习实验、快速原型开发和文档完善的算法实现。最适合单智能体与 Gymnasium 环境结合使用。如需高性能并行训练、多智能体系统或自定义向量化环境，请改用 pufferlib。