Roboschool also makes it easy to train multiple agents together in the same environment.

After we launched Gym⁠(opens in a new window), one issue we heard from many users was that the MuJoCo⁠(opens in a new window) component required a paid license (though MuJoCo recently added free⁠(opens in a new window) student licenses for personal and class work). Roboschool removes this constraint, letting everyone conduct research regardless of their budget. Roboschool is based on the Bullet Physics Engine⁠(opens in a new window), an open-source, permissively licensed⁠(opens in a new window) physics library that has been used by other simulation software such as Gazebo⁠(opens in a new window) and V-REP⁠(opens in a new window).

Roboschool ships with twelve environments, including tasks familiar to Mujoco users as well as new challenges, such as harder versions of the Humanoid walker task, and a multi-player Pong environment. We plan to expand this collection over time and look forward to the community contributing as well.

For the existing MuJoCo environments, besides porting them to Bullet, we have modified them to be more realistic. Here are three of the environments we ported, with explanations of how they differ from the existing environments.