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 A
OpenAI
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.
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:
- The need for better benchmarks. In supervised learning, progress has been driven by large labeled datasets like ImageNet(opens in a new window). In RL, the closest equivalent would be a large and diverse collection of environments. However, the existing open-source collections of RL environments don’t have enough variety, and they are often difficult to even set up and use.
- Lack of standardization of environments used in publications. Subtle differences in the problem definition, such as the reward function or the set of actions, can drastically alter a task’s difficulty. This issue makes it difficult to reproduce published research and compare results from different papers.
OpenAI Gym is an attempt to fix both problems.
We’ve made it easy to upload results(opens in a new window) to OpenAI Gym. However, we’ve opted not to create traditional leaderboards. What matters for research isn’t your score (it’s possible to overfit or hand-craft solutions to particular tasks), but instead the generality of your technique.
We’re starting out by maintaining a curated list(opens in a new window) of contributions that say something interesting about algorithmic capabilities. Long-term, we want this curation to be a community effort rather than something owned by us. We’ll necessarily have to figure out the details over time, and we’d would love your help(opens in a new window) in doing so.