Gym provides a toolkit to benchmark AI-based tasks. The interface is easy to use. The goal is to enable reproducible research. Visit https://gym.openai.com for more information about Gym. An agent can be taught inside of the gym, and learn activities such as playing games or walking. An environment is a library of problems.
The standard set of problems presented in the gym are as follows:
- Space Invaders
- Lunar Lander
- Mountain Car
- Car Racing
- Bipedal Walker
Any algorithm can work out in the gym by training for these activities. All of the problems have the same interface. Therefore, any general reinforcement learning algorithm can be used through the interface.