# My tuner cannot stop as expected

**URL:** <https://discuss.ray.io/t/my-tuner-cannot-stop-as-expected/9864>\
**Category:** RLlib\
**Created:** [March 23, 2023, 12:04pm UTC](https://discuss.ray.io/t/my-tuner-cannot-stop-as-expected/9864 "2023-03-23T12:04:41Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![jiangzhangze](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/jiangzhangze/32/4037_2.png) [@jiangzhangze](https://discuss.ray.io/u/jiangzhangze)\
**Post date:** [March 23, 2023, 12:04pm UTC](https://discuss.ray.io/t/my-tuner-cannot-stop-as-expected/9864/1 "2023-03-23T12:04:41Z")

</div>

I’m trying to train a PPO with a custom env followed [this tutorial](https://github.com/anyscale/academy/blob/main/ray-rllib/acm_recsys_tutorial_2022/01_intro_gym_and_rllib_optional.ipynb).But my tuner didn’t stop until I stop it by hand.And some informations such as reward and episode don’t show in log.  
Here are the train.py：

```auto
import ray
from ray.rllib.algorithms import ppo
from envs.my_env import PathPlanning
from ray.tune import register_env
def env_creator(env_config):
    return PathPlanning(env_config)
register_env("PathPlanning", env_creator)
ray.init()
ppo_config = ppo.PPOConfig()
ppo_config.environment(env="CartPole-v0")
ppo_config.framework(framework="tf2")
ppo_config.debugging(seed=415, log_level="ERROR")
ppo_config.evaluation(
    evaluation_interval=15,
    evaluation_duration=5,
    evaluation_num_workers=4,
    evaluation_parallel_to_training=True,
    evaluation_config=dict(
        explore=False,
        num_workers=2,
    ),
)
ppo_config.rollouts(num_rollout_workers=4,
                    num_envs_per_worker=1)
ppo_algo = ppo_config.build()

ppo_config.training(lr=ray.tune.grid_search([5e-5, 2e-5]),
                    train_batch_size=ray.tune.grid_search([128, 256]))

stop = dict(
    timesteps_total=100,
    trainning_iteration=5
)
tuner = ray.tune.Tuner(
    ppo_config.algo_class,

    param_space=ppo_config.to_dict(),

    run_config=ray.air.RunConfig(
        local_dir="my_Tune_logs",
        stop=stop,
        verbose=3,
    )
)

experiment_results = tuner.fit()

```

And here are the log：

```auto
== Status ==
Current time: 2023-03-23 20:02:11 (running for 00:00:05.18)
Memory usage on this node: 13.9/15.8 GiB 
Using FIFO scheduling algorithm.
Resources requested: 0/12 CPUs, 0/1 GPUs, 0.0/3.06 GiB heap, 0.0/1.53 GiB objects
Result logdir: E:\AI\rllib\my_env\PathPlanning\my_Tune_logs\PPO_2023-03-23_20-02-06
Number of trials: 4/4 (4 PENDING)
+-----------------------------+----------+-------+-------+--------------------+
| Trial name | status | loc | lr | train_batch_size |
|-----------------------------+----------+-------+-------+--------------------|
| PPO_CartPole-v0_8843a_00000 | PENDING | | 5e-05 | 128 |
| PPO_CartPole-v0_8843a_00001 | PENDING | | 2e-05 | 128 |
| PPO_CartPole-v0_8843a_00002 | PENDING | | 5e-05 | 256 |
| PPO_CartPole-v0_8843a_00003 | PENDING | | 2e-05 | 256 |
+-----------------------------+----------+-------+-------+--------------------+

```

In addition，there are JASON files and PKL files in the “logs” folder.But tensorboard showed nothing.

---

<div class="post-metadata">

**Author:** ![mannyv](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/mannyv/32/606_2.png) [@mannyv](https://discuss.ray.io/u/mannyv)\
**Post date:** [March 23, 2023, 1:44pm UTC](https://discuss.ray.io/t/my-tuner-cannot-stop-as-expected/9864/2 "2023-03-23T13:44:00Z")

</div>

Hi @jiangzhangze,

The statud=pending means that none of them started training. Usually this means you requested more resources than you have available.

---

<div class="post-metadata">

**Author:** ![jiangzhangze](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/jiangzhangze/32/4037_2.png) [@jiangzhangze](https://discuss.ray.io/u/jiangzhangze)\
**Post date:** [March 24, 2023, 5:03am UTC](https://discuss.ray.io/t/my-tuner-cannot-stop-as-expected/9864/3 "2023-03-24T05:03:24Z")

</div>

Hi@mannyv,thanks for your reply.According to [tutorial](https://github.com/anyscale/academy/blob/main/ray-rllib/acm_recsys_tutorial_2022/01_intro_gym_and_rllib_optional.ipynb), total number of ray actor= num\_workers + num\_rollout\_workers + evaluation\_num\_workers + 1.But the code above required `4 + 2 + 4 + 1 = 11<12(my cpus)`,why did this happen?