# Inconsistent number of episodes during evaluation **URL:** \ **Category:** RLlib\ **Created:** [May 7, 2021, 1:31pm UTC](https://discuss.ray.io/t/inconsistent-number-of-episodes-during-evaluation/2090 "2021-05-07T13:31:49Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![Rory](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/rory/32/688_2.png) [@Rory](https://discuss.ray.io/u/Rory)\ **Post date:** [May 7, 2021, 1:31pm UTC](https://discuss.ray.io/t/inconsistent-number-of-episodes-during-evaluation/2090/1 "2021-05-07T13:31:49Z")
Hi there, I’ve been playing around with the evaluation routine with the trainers. I’m having difficulty getting the rollout workers to do a consistent number of evaluations per time. For example, if I set the evaluation\_num\_episodes to 300 with 3 workers, so the evaluate routine calls worker.sample.remote() 300 times. With the default config I have a very variable number of episodes per evaluation: (len is mean episode\_len) ``` episodes: 445, len: 11.3 episodes: 582, len: 7.5 episodes: 442, len: 11.2 episodes: 450, len: 10.5 episodes: 429, len: 11.1 episodes: 442, len: 10.8 episodes: 551, len: 8.3 episodes: 409, len: 11.5 episodes: 479, len: 10.0 episodes: 404, len: 12.3 episodes: 450, len: 10.8 episodes: 383, len: 13.0 episodes: 401, len: 12.4 episodes: 374, len: 13.8 episodes: 411, len: 11.7 episodes: 370, len: 13.5 episodes: 381, len: 13.4 episodes: 350, len: 14.7 episodes: 324, len: 16.3 episodes: 339, len: 15.8 ``` With rollout\_fragment\_length set to 1 I get better results: ``` episodes: 310, len: 11.2 episodes: 294, len: 7.3 episodes: 302, len: 11.7 episodes: 300, len: 11.0 episodes: 300, len: 11.2 episodes: 295, len: 10.9 episodes: 305, len: 8.5 episodes: 299, len: 12.3 episodes: 301, len: 10.5 episodes: 302, len: 12.6 episodes: 295, len: 11.1 episodes: 302, len: 13.9 episodes: 300, len: 12.4 episodes: 298, len: 12.4 episodes: 303, len: 12.2 episodes: 299, len: 13.8 episodes: 300, len: 14.1 episodes: 300, len: 14.4 episodes: 296, len: 16.3 episodes: 304, len: 15.4 ``` However it’s still pretty inconsistent which is frustrating and sometimes it’s now less than the specified number of episodes which I think is worse. the batch mode didn’t seem to have any effect on the numbers. Is there any better way to sample evaluations, or have I just missed a configuration option? Cheers, Rory ---
**Author:** ![smorad](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/smorad/32/272_2.png) [@smorad](https://discuss.ray.io/u/smorad)\ **Post date:** [May 11, 2021, 10:53pm UTC](https://discuss.ray.io/t/inconsistent-number-of-episodes-during-evaluation/2090/2 "2021-05-11T22:53:54Z")
> [@Rory](#): > > evaluation routine with the trainers. I’m having difficulty getting the rollout workers to do a consistent number of evaluations per time. > > For example, if I set the evaluation\_num\_episodes to 300 with 3 workers, so the evaluate routine calls worker.sample.remote() 300 times. > With the default config I have a very variable number of episodes per evaluation: (len is mean episode\_len) > > ```auto > > ``` You want to use a low-throughput algorithm. `IMPALA/APE-X` will run the trainer in its own loop, so after finishing a batch, it will start training on whatever is in the queue. If the queue is not full, it will train on fewer episodes.