# Trainer.evaluate() runs 1 extra episode instead of as defined in evaluation\_duration

**URL:** <https://discuss.ray.io/t/trainer-evaluate-runs-1-extra-episode-instead-of-as-defined-in-evaluation-duration/7316>\
**Category:** RLlib\
**Created:** [August 24, 2022, 7:54am UTC](https://discuss.ray.io/t/trainer-evaluate-runs-1-extra-episode-instead-of-as-defined-in-evaluation-duration/7316 "2022-08-24T07:54:12Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![hridayns](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/hridayns/32/1222_2.png) [@hridayns](https://discuss.ray.io/u/hridayns)\
**Post date:** [August 24, 2022, 7:54am UTC](https://discuss.ray.io/t/trainer-evaluate-runs-1-extra-episode-instead-of-as-defined-in-evaluation-duration/7316/1 "2022-08-24T07:54:12Z")

</div>

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

- High: It blocks me to complete my task.

I am simple trying to evaluate a model from a checkpoint for 10 episodes. I am unable to use tune for evaluation as it just seems impossibly complicated to manage the number of episodes it will run - I have no idea why.

Instead, I have moved to try using trainer.evaluate() after restoring my checkpoint using trainer.restore(). This seems to do what I need, minus the auto-generated result information (in Tune) and the fact that it always runs 1 more episode than that defined in the **evaluation\_duration** config parameter.

Why is this the case? And how can I fix it? These are the evaluation-related configuration options I have set:

```auto
# Evaluation settings
policy_conf['evaluation_interval'] = 0
policy_conf['evaluation_duration'] = 10 # change to 1 episode?
policy_conf['evaluation_duration_unit'] = 'episodes'
policy_conf['evaluation_parallel_to_training'] = False
policy_conf['in_evaluation'] = False
policy_conf['evaluation_config'] = {}
policy_conf['evaluation_num_workers'] = 1
policy_conf['custom_eval_function'] = None
policy_conf['always_attach_evaluation_results'] = True
policy_conf['sample_async'] = False

```

Let me know if any other information is required. I would appreciate any help at all, on the matter. Thank you.

---

<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:** [August 26, 2022, 1:37pm UTC](https://discuss.ray.io/t/trainer-evaluate-runs-1-extra-episode-instead-of-as-defined-in-evaluation-duration/7316/2 "2022-08-26T13:37:10Z")

</div>

Hi @hridayns,

Have you tried this in the latest release? 2.0. There were some issues with 1.13 running too many evaluations [[RLlib] Excessive evaluation if rollout\_fragment\_length \< timesteps\_per\_iteration · Issue #27821 · ray-project/ray · GitHub](https://github.com/ray-project/ray/issues/27821) but that has been fixed in the latest release.