Hands-On Intelligent Agents with OpenAI Gym

Quickstart guide to setup and run Gym Retro

Let's try out the Gym Retro library quickly by installing the pre-built binaries using pip with the following command:

          (rl_gym_book) praveen@ubuntu:~/rl_gym_book/ch9$ pip install gym-retro
        

Once the installation is successful, we can have a sneak peek into one of the available Gym Retro environments using the following script:

          #!/usr/bin/env pythonimport
          retro
          
          if
          __name__
          ==
          '__main__'
          :
             env
          =
          retro
          .
          make
          (
          game
          =
          'Airstriker-Genesis'
          ,
          state
          =
          'Level1'
          )
          obs
          =
          env
          .
          reset
          ()
          while
          True
          :
          obs
          ,
          rew
          ,
          done
          ,
          info
          =
          env
          .
          step
          (
          env
          .
          action_space
          .
          sample
          ())
          env
          .
          render
          ()
          if
          done
          :
          obs
          =
          env
          .
          reset
          ()
        

Running this script will bring up a window with the Airstriker game and show the spaceship ...