Use existing numerical computation libraries, such as TensorFlow or Theano.
Universe allows an AI agent to easily interact with any computer program.
Observe the program the same way a person does, by looking at the pixels.
Act using the same controls as a person, by using keyboard and mouse.
Solve successively harder environments to develop general problem solving ability.
Solve and learn 1000s of environments to develop common sense — the ability to rapidly solve a new problem.
Most AI agents are trained to solve individual tasks one at a time. Create sophisticated, flexible agents by training them on a diverse suite of tasks.
Compare and share benchmarks with the wider community.
Universe supports agents which learn across tasks, developing general-purpose knowledge about the world.
Turn any program into an environment, or train across existing ones. Universe doesn't need access to program internals, source code, or bot APIs.
import gym import universe # register the universe environments env = gym.make('flashgames.DuskDrive-v0') env.configure(remotes=1) # create one flashgames Docker container observation_n = env.reset() while True: # your agent generates action_n at 60 frames per second action_n = [[('KeyEvent', 'ArrowUp', True)] for ob in observation_n] observation_n, reward_n, done_n, info = env.step(action_n) env.render()