joint ppo ray example

class MultiEnv(gym.Env):
    def __init__(self, env_config):
        # pick actual env based on worker and env indexes
        #print("worker index is {}".format(env_config.worker_index))
        #print("testing vector_index {}".format(env_config.vector_index))
        #BustAMove.Challengeplay0
        challenge_level = env_config.worker_index % 5
        self.env = sonic_on_ray.make(game='BustAMove-Snes', state='BustAMove.Challengeplay{}'.format(challenge_level)) #BustAMove.1pplay.Level10
        self.action_space = self.env.action_space
        self.observation_space = self.env.observation_space
    def reset(self):
        return self.env.reset()
    def step(self, action):
        return self.env.step(action)

register_env("multienv", lambda c: MultiEnv(c))