Function run_worker

distributed/rpc/rl/main.py:210–238

r""" This is the entry point for all processes. The rank 0 is the agent. All other ranks are observers.

(rank, world_size)

def run_worker(rank, world_size):
    r"""
    This is the entry point for all processes. The rank 0 is the agent. All
    other ranks are observers.
    """
    os.environ['MASTER_ADDR'] = 'localhost'
    os.environ['MASTER_PORT'] = '29500'
    if rank == 0:
        # rank0 is the agent
        rpc.init_rpc(AGENT_NAME, rank=rank, world_size=world_size)

        agent = Agent(world_size)
        for i_episode in count(1):
            n_steps = int(TOTAL_EPISODE_STEP / (args.world_size - 1))
            agent.run_episode(n_steps=n_steps)
            last_reward = agent.finish_episode()

            if i_episode % args.log_interval == 0:
                print('Episode {}\tLast reward: {:.2f}\tAverage reward: {:.2f}'.format(
                      i_episode, last_reward, agent.running_reward))

            if agent.running_reward > agent.reward_threshold:
                print("Solved! Running reward is now {}!".format(agent.running_reward))
                break
    else:
        # other ranks are the observer
        rpc.init_rpc(OBSERVER_NAME.format(rank), rank=rank, world_size=world_size)
        # observers passively waiting for instructions from agents
    rpc.shutdown()


def main():