I’m really excited about the first major release of the OpenAI Lab. It’s an experimentation framework for reinforcement learning using the OpenAI Gym, Tensorflow, and Keras. We are currently porting it to pyTorch.
OpenAI Lab is created to do reinforcement learning (RL) like science – theorize, experiment. It provides an easy interface to the OpenAI Gym and deep learning libraries, with an automated experimentation and evaluation framework, and a number of customizable algorithms available out of the box.