Tianshou: a Highly Modularized Deep Reinforcement Learning Library

We present Tianshou, a highly modularized python library for deep reinforcement learning (DRL) that uses PyTorch as its backend. Tianshou provides a flexible, reliable, yet simple implementation of a modular DRL library, and has supported more than 20 classic algorithms succinctly through a unified interface. To facilitate related research and prove Tianshou's reliability, we have released Tianshou's benchmark on MuJoCo environments, covering eight classic algorithms with the state-of-the-art performance. We open-sourced Tianshou at https://github.com/thu-ml/tianshou/, which has received over 3.7k stars and become one of the most popular PyTorch-based DRL libraries.