Tianshou: An elegant deep reinforcement learning library

Tianshou is a deep reinforcement learning library based on pure PyTorch. It caters to the needs of researchers and practitioners alike by offering a mix of low-level interfaces for maximum control and high-level interfaces for ease of use. It supports a wide range of state-of-the-art algorithms, all implementations being optimised for speed.

In Chinese, Tianshou means divinely ordained and is derived from the gift of being born. Tianshou is a reinforcement learning platform, and the nature of reinforcement learning is to not explicitly learn from a teacher (as in supervised learning) but rather to learn by oneself through constant interaction with the environment. It thus complements the scope of sensAI: The Python Library for Sensible AI which is named after a Japanese term for teacher (“sensei”).

Supported Algorithms

Tianshou supports a wide variety of algorithms: