import ray
import ray.rllib.agents.ppo as ppo
from ray import serve

def train_ppo_model():
    trainer = ppo.PPOTrainer(
        config={"framework": "torch", "num_workers": 0},
        env="CartPole-v0",
    )
    # Train for one iteration
    trainer.train()
    trainer.save("/tmp/rllib_checkpoint")
    return "/tmp/rllib_checkpoint/checkpoint_000001/checkpoint-1"


checkpoint_path = train_ppo_model()

# This can be useful if you don't want to clutter the page with details.

import ray
import ray.rllib.agents.ppo as ppo
from ray import serve

ray.shutdown()