# PPO Policy not respecting action-space bounds

**URL:** <https://discuss.ray.io/t/ppo-policy-not-respecting-action-space-bounds/15075>\
**Category:** RLlib\
**Created:** [June 27, 2024, 12:19pm UTC](https://discuss.ray.io/t/ppo-policy-not-respecting-action-space-bounds/15075 "2024-06-27T12:19:54Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![RC77RC](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/rc77rc/32/6265_2.png) [@RC77RC](https://discuss.ray.io/u/RC77RC)\
**Post date:** [June 27, 2024, 12:19pm UTC](https://discuss.ray.io/t/ppo-policy-not-respecting-action-space-bounds/15075/1 "2024-06-27T12:19:54Z")

</div>

**How severe does this issue affect your experience of using Ray?**

- High: It blocks me to complete my task.

I have defined an environment that has the following action space:

`self.action_space=Box(low=np.array([0.01,0.01,0,0.01,0.01,1]),high=np.array([25,5,3,1,1,15]))`

Then, I used PPO to train an agent on this environment. During training, the bounds are respected and no problems arise.

However, I now wanted to use the policy that resulted from training. To do so, I have the following code:

```auto
agent = Policy.from_checkpoint(path_to_checkpoint)['default_policy']
action = agent.compute_single_action(state)[0]

```

However, this constantly generates actions that fall outside of the predefined bounds. How can I correct this? I tried to change

```auto
agent.config["clip_actions"] = True

```

or doing

```auto
action = agent.compute_single_action(state,clip_actions=True)[0]

```

but the problem was not solved.

Any help is appreciated.  
Thanks!