# What is the expected success rate for a ACT trained model using 50 episodes

> Source: <https://discuss.huggingface.co/t/what-is-the-expected-success-rate-for-a-act-trained-model-using-50-episodes/178517#post_2>
> Published: 2026-08-09 06:39:06+00:00

For now, I think I found a few cases that seem fairly close:

**Short answer:** I would not expect there to be a useful universal number like “ACT trained on 50 episodes should succeed X% of the time.” Fifty demonstrations is a very reasonable *starting recipe*, but it is not a success-rate benchmark.

The current [LeRobot imitation-learning tutorial](https://huggingface.co/docs/lerobot/il_robots) recommends **at least 50 episodes, roughly 10 per location**, while keeping the cameras fixed and the grasping behavior consistent. The [ACT documentation](https://huggingface.co/docs/lerobot/act) also describes ACT as often being quite data-efficient at around 50 demonstrations. But the original [ACT/ALOHA results](https://tonyzhaozh.github.io/aloha/) are very task/setup-specific: they used 50 demonstrations per task, ran the policy at 50 Hz, randomized object position along a defined 15 cm range for both training and testing, and reported 96%, 84%, 64%, and 92% on four different tasks. So even the original 50-demo results span a fairly large range.

For your particular symptoms, I think there are **two separate questions** worth keeping apart:

And there is a third, somewhat independent clue: the **5.6 Hz warning**.

Your shortened source path ends in:

```
...gies/base.py:75
```

If you are using the newer LeRobot rollout stack (for example v0.6.1), that suffix is very suggestive of [ lerobot/rollout/strategies/base.py](https://github.com/huggingface/lerobot/blob/v0.6.1/src/lerobot/rollout/strategies/base.py). The important and slightly confusing detail is that

`BaseStrategy`

is explicitly the 

```
Record loop is running slower (...) than the target FPS (...).
Dataset frames might be dropped and robot control might be unstable.
```

So if that is the actual full path, the warning text by itself does **not** prove that your 50 training demonstrations were recorded at 5.6 Hz. It may instead be describing the policy rollout/control loop. LeRobot v0.6.0 introduced the dedicated [ lerobot-rollout](https://huggingface.co/blog/lerobot-release-v060) workflow, so the exact command/version matters here.

On the other hand, [ lerobot_record.py](https://github.com/huggingface/lerobot/blob/v0.6.1/src/lerobot/scripts/lerobot_record.py) also has a slow-loop warning with almost identical wording. So I would not guess from the message alone:

`lerobot-record`

or `lerobot-rollout`

is the highest-information discriminator.A compact way to think about it is:

```
Where is the 5.6 Hz warning actually coming from?
│
├─ rollout/strategies/base.py
│  └─ Treat it primarily as a rollout/control-loop problem.
│     It does not, by itself, say the training dataset was captured at 5.6 Hz.
│
└─ actual lerobot-record path is also running around 5.6 Hz
   └─ Inspect the already-recorded dataset before collecting more episodes,
      because nominal 30 FPS and actual capture/control cadence may disagree.

Then separate the behavior:
│
├─ demonstrated positions work; held-out positions fail
│  └─ data coverage / generalization is the leading branch
│
└─ demonstrated positions also miss consistently to the right
   └─ calibration / camera geometry / config / timing deserves its own branch
```

If I were trying to minimize the amount of rework, that is the order I would use rather than immediately recording another 50 episodes.

A few fairly close real-world ACT casesI would **not throw away the 50 episodes yet, and I would not immediately collect another 50 either**.

The lowest-cost sequence seems to be:

`lerobot-info`

and note the exact LeRobot version.`lerobot-record`

vs `lerobot-rollout`

, and strategy if applicable).That should turn “Is 50 episodes enough?” into a much more useful answer:

```
Is the dataset/control path healthy?
        ↓
Can it reproduce the demonstrated distribution?
        ↓
How far does it generalize outside that distribution?
```

If the first two are healthy, then increasing *coverage* rather than simply increasing the raw episode count becomes a much more defensible next experiment.