Welcome to Reinforcement Learning Zoo!


RLzoo is a collection of the most practical reinforcement learning algorithms, frameworks and applications, released on Github in November 2019. It is implemented with Tensorflow 2.0 and API of neural network layers in TensorLayer 2, to provide a hands-on fast-developing approach for reinforcement learning practices and benchmarks. It supports basic toy-test environments like OpenAI Gym and DeepMind Control Suite with very simple configurations. Moreover, RLzoo supports robot learning benchmark environment RLBench based on Vrep/Pyrep simulator. Other large-scale distributed training framework for more realistic scenarios with Unity 3D, Mujoco, Bullet Physics, etc, will be supported in the future.

We also provide novices friendly DRL Tutorials for algorithms implementation, where each algorithm is implemented in an individual script. The tutorials serve as code examples for our Springer textbook Deep Reinforcement Learning: Fundamentals, Research and Applications , you can get the free PDF if your institute has Springer license.

Other Resources


This project is under active development, if you want to join the core team, feel free to contact Zihan Ding at zhding[at]mail.ustc.edu.cn