OpenAI Gym Beta

We’re releasing the public beta of OpenAI Gym, a toolkit for developing and comparing reinforcement learning (RL) algorithms. It consists of a growing suite of environments (from simulated robots to Atari games), and a site for comparing and reproducing results.

OpenAI Gym is compatible with algorithms written in any framework, such as Tensorflow⁠(opens in a new window) and Theano⁠(opens in a new window). The environments are written in Python, but we’ll soon make them easy to use from any language. We originally built OpenAI Gym as a tool to accelerate our own RL research. We hope it will be just as useful for the broader community.

Getting started

Why RL?

Reinforcement learning (RL) is the subfield of machine learning concerned with decision making and motor control. It studies how an agent can learn how to achieve goals in a complex, uncertain environment. It’s exciting for two reasons:

• RL is very general, encompassing all problems that involve making a sequence of decisions: for example, controlling a robot’s motors so that it’s able to run⁠(opens in a new window) and jump⁠(opens in a new window), making business decisions like pricing and inventory management, or playing video games⁠(opens in a new window) and board games⁠(opens in a new window). RL can even be applied to supervised learning problems with sequential⁠(opens in a new window) or⁠(opens in a new window) structured⁠(opens in a new window) outputs.

• RL algorithms have started to achieve good results in many difficult environments. RL has a long history, but until recent advances in deep learning, it required lots of problem-specific engineering. DeepMind’s Atari results⁠(opens in a new window), BRETT⁠(opens in a new window) from Pieter Abbeel’s⁠ group, and AlphaGo⁠(opens in a new window) all used deep RL algorithms which did not make too many assumptions about their environment, and thus can be applied in other settings.

However, RL research is also slowed down by two factors: