The gym comes prepackaged with many many environments. It's this common API around many environments that makes the gym so great. Here we will list additional environments that do not come prepacked with the gym. Submit another to this list via a pull-request.
NOTICE: Its possible that in time OpenAI will develop a full fledged repository of supplemental environments. Until then this bit of markdown will suffice.
PGE is a FOSS 3D engine for AI simulations, and can interoperate with the Gym. Contains environments with modern 3D graphics, and uses Bullet for physics.
Learn more here: https://github.com/222464/PGE
gym-inventory is a single agent domain featuring discrete state and action spaces that an AI agent might encounter in inventory control problems.
Learn more here: https://github.com/paulhendricks/gym-inventory
gym-gazebo presents an extension of the initial OpenAI gym for robotics using ROS and Gazebo, an advanced 3D modeling and rendering tool.
Learn more here: https://github.com/erlerobot/gym-gazebo/
A simple 2D maze environment where an agent finds its way from the start position to the goal.
Learn more here: https://github.com/tuzzer/gym-maze/
A minimalistic gridworld environment. Seeks to minimize software dependencies, be easy to extend and deliver good performance for faster training.
Learn more here: https://github.com/maximecb/gym-minigrid
The environment consists of transportation puzzles in which the player's goal is to push all boxes on the warehouse's storage locations. The advantage of the environment is that it generates a new random level every time it is initialized or reset, which prevents over fitting to predefined levels.
Learn more here: https://github.com/mpSchrader/gym-sokoban
A lane-following simulator built for the Duckietown project (small-scale self-driving car course).
Learn more here: https://github.com/duckietown/gym-duckietown