lerobot-clone/docs/source/bring_your_own_policies.mdx

# Adding a Policy

This guide walks you through implementing a custom policy and getting it to work with LeRobot's training, evaluation, and deployment tools. There are two paths:

- **Plugin (out-of-tree)** — ship your policy as a standalone `lerobot_policy_*` package. Faster, no PR required, easy to iterate. Right for experimentation, internal use, or when you want to publish independently.
- **In-tree (contributed to LeRobot)** — land your policy directly in `src/lerobot/policies/`. Requires a PR, but makes your policy a first-class citizen of the library.

The plugin route is usually the right starting point — promote to in-tree once the policy has stabilized and there's clear value in shipping it with the library.

Either way, the building blocks are the same: a configuration class, a policy class, and a processor factory. The first half of this guide covers those shared pieces; the second half covers the path-specific scaffolding ([Path A](#path-a-out-of-tree-plugin), [Path B](#path-b-contributing-in-tree)).

A note on tone: robot-learning is an actively evolving field, and "what a policy looks like" can shift with each new architecture. The conventions described here exist because they let `lerobot-train` and `lerobot-eval` work uniformly across very different models. When a new policy genuinely doesn't fit them, raise it (in your PR, or an issue) — the conventions are not sacred.

---

## Anatomy of a policy

Three building blocks make up every policy. The names below use `my_policy` as a placeholder — replace with your policy's name. That name is load-bearing: it must match the string you pass to `@PreTrainedConfig.register_subclass`, the `MyPolicy.name` class attribute, and the `make_<name>_pre_post_processors` factory function (more on each below).

### Configuration class

Inherit from [`PreTrainedConfig`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/configs/policies.py) and register your policy type. Here is a template — customize the parameters and methods as needed for your policy's architecture and training requirements.

```python
# configuration_my_policy.py
from dataclasses import dataclass, field
from lerobot.configs import PreTrainedConfig
from lerobot.optim import AdamWConfig
from lerobot.optim import CosineDecayWithWarmupSchedulerConfig

@PreTrainedConfig.register_subclass("my_policy")
@dataclass
class MyPolicyConfig(PreTrainedConfig):
    """Configuration class for MyPolicy.

    Args:
        n_obs_steps: Number of observation steps to use as input
        horizon: Action prediction horizon
        n_action_steps: Number of action steps to execute
        hidden_dim: Hidden dimension for the policy network
        # Add your policy-specific parameters here
    """

    horizon: int = 50
    n_action_steps: int = 50
    hidden_dim: int = 256

    optimizer_lr: float = 1e-4
    optimizer_weight_decay: float = 1e-4

    def __post_init__(self):
        super().__post_init__()
        if self.n_action_steps > self.horizon:
            raise ValueError("n_action_steps cannot exceed horizon")

    def validate_features(self) -> None:
        """Validate input/output feature compatibility.

        Call this explicitly from your policy's __init__ — the base class does not.
        """
        if not self.image_features:
            raise ValueError("MyPolicy requires at least one image feature.")
        if self.action_feature is None:
            raise ValueError("MyPolicy requires 'action' in output_features.")

    def get_optimizer_preset(self) -> AdamWConfig:
        return AdamWConfig(lr=self.optimizer_lr, weight_decay=self.optimizer_weight_decay)

    def get_scheduler_preset(self):
        """Return a LRSchedulerConfig from lerobot.optim, or None."""
        return None

    @property
    def observation_delta_indices(self) -> list[int] | None:
        """Relative timestep offsets the dataset loader provides per observation.

        Return `None` for single-frame policies. For temporal policies that consume
        multiple past or future frames, return a list of offsets, e.g. `[-20, -10, 0, 10]` for
        3 past frames at stride 10 and 1 future frame at stride 10.
        """
        return None

    @property
    def action_delta_indices(self) -> list[int]:
        """Relative timestep offsets for the action chunk the dataset loader returns."""
        return list(range(self.horizon))

    @property
    def reward_delta_indices(self) -> None:
        return None
```

The string you pass to `@register_subclass` must match `MyPolicy.name` (next section) and is what users supply as `--policy.type` on the CLI. Default to `AdamW` from `lerobot.optim` for `get_optimizer_preset` unless you genuinely need otherwise.

### Policy class

Inherit from [`PreTrainedPolicy`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/policies/pretrained.py) and set two class attributes — both are checked by `__init_subclass__`:

```python
# modeling_my_policy.py
import torch
import torch.nn as nn
from typing import Any

from lerobot.policies import PreTrainedPolicy
from lerobot.utils.constants import ACTION
from .configuration_my_policy import MyPolicyConfig

class MyPolicy(PreTrainedPolicy):
    config_class = MyPolicyConfig  # must match the string in @register_subclass
    name = "my_policy"

    def __init__(self, config: MyPolicyConfig, dataset_stats: dict[str, Any] = None):
        super().__init__(config, dataset_stats)
        config.validate_features()  # not called automatically by the base class
        self.config = config
        self.model = ...  # your nn.Module here

    def reset(self):
        """Reset per-episode state. Called by lerobot-eval at the start of each episode."""
        ...

    def get_optim_params(self) -> dict:
        """Return parameters to pass to the optimizer (e.g. with per-group lr/wd)."""
        return {"params": self.parameters()}

    def predict_action_chunk(self, batch: dict[str, torch.Tensor], **kwargs) -> torch.Tensor:
        """Return the full action chunk (B, chunk_size, action_dim) for the current observation."""
        ...

    def select_action(self, batch: dict[str, torch.Tensor], **kwargs) -> torch.Tensor:
        """Return a single action for the current timestep (called every step at inference)."""
        ...

    def forward(self, batch: dict[str, torch.Tensor]) -> tuple[torch.Tensor, dict | None]:
        """Compute the training loss.

        Returns `(loss, output_dict)`. `output_dict` may be `None`; everything in it must be
        logging-friendly Python natives (no tensors with gradients).

        `batch["action_is_pad"]` is a bool mask of shape (B, horizon) that marks
        timesteps padded because the episode ended before `horizon` steps; you
        can exclude those from your loss.
        """
        actions = batch[ACTION]
        action_is_pad = batch.get("action_is_pad")
        ...
        return loss, {"some_loss_component": some_loss_component.item()}
```

The methods called by the train/eval loops:

| Method                                                            | Used by           | What it does                                                                                                                                                                                                                                         |
| ----------------------------------------------------------------- | ----------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `reset() -> None`                                                 | `lerobot-eval`    | Clear per-episode state at the start of each episode.                                                                                                                                                                                                |
| `select_action(batch, **kwargs) -> Tensor`                        | `lerobot-eval`    | Return the next action `(B, action_dim)`. Called every step.                                                                                                                                                                                         |
| `predict_action_chunk(batch, **kwargs) -> Tensor`                 | the policy itself | Return an action chunk `(B, chunk_size, action_dim)`. Currently abstract on the base class — raise `NotImplementedError` if your policy doesn't chunk.                                                                                               |
| `forward(batch, reduction="mean") -> tuple[Tensor, dict \| None]` | `lerobot-train`   | Return `(loss, output_dict)`. Accept `reduction="none"` if you want to support per-sample weighting.                                                                                                                                                 |
| `get_optim_params() -> dict`                                      | the optimizer     | Return `self.parameters()` for simple policies; return a named parameter dict for [multi-optimizer policies](https://github.com/huggingface/lerobot/blob/ecd38c50d7d15b4184cf42649ff1185ee2e11eeb/src/lerobot/policies/sac/modeling_sac.py#L61-L73). |
| `update() -> None` _(optional)_                                   | `lerobot-train`   | Called after each optimizer step _if defined_. Use for EMA, target nets, replay buffers (TDMPC uses this).                                                                                                                                           |

Batches are flat dictionaries keyed by the constants in [`lerobot.utils.constants`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/utils/constants.py): `OBS_STATE` (`observation.state.<motor>`), `OBS_IMAGES` (`observation.images.<camera>`), `OBS_LANGUAGE`, `ACTION`, etc. Reuse the constants — don't invent new prefixes.

### Processor functions

LeRobot uses `PolicyProcessorPipeline`s to normalize inputs and de-normalize outputs around your policy. For a concrete reference, see [`processor_act.py`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/policies/act/processor_act.py) or [`processor_diffusion.py`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/policies/diffusion/processor_diffusion.py).

```python
# processor_my_policy.py
from typing import Any
import torch

from lerobot.processor import PolicyAction, PolicyProcessorPipeline


def make_my_policy_pre_post_processors(
    config,
    dataset_stats: dict[str, dict[str, torch.Tensor]] | None = None,
) -> tuple[
    PolicyProcessorPipeline[dict[str, Any], dict[str, Any]],
    PolicyProcessorPipeline[PolicyAction, PolicyAction],
]:
    preprocessor = ...   # build your PolicyProcessorPipeline for inputs
    postprocessor = ...  # build your PolicyProcessorPipeline for outputs
    return preprocessor, postprocessor
```

**Important — function naming:** LeRobot discovers your processor by name. The function **must** be called `make_{policy_name}_pre_post_processors` (matching the string you passed to `@PreTrainedConfig.register_subclass`).

---

## Path A: Out-of-tree plugin

The fastest way to ship a policy: package it as a standalone Python distribution and install it alongside LeRobot. No PR required, you own the release cycle, and you can publish to PyPI under your own namespace.

### Package structure

Create a package with the prefix `lerobot_policy_` (IMPORTANT!) followed by your policy name:

```bash
lerobot_policy_my_policy/
├── pyproject.toml
└── src/
    └── lerobot_policy_my_policy/
        ├── __init__.py
        ├── configuration_my_policy.py
        ├── modeling_my_policy.py
        └── processor_my_policy.py
```

### `pyproject.toml`

```toml
[project]
name = "lerobot_policy_my_policy"
version = "0.1.0"
dependencies = [
    # your policy-specific dependencies
]
requires-python = ">= 3.12"

[build-system]
build-backend = # your-build-backend
requires = # your-build-system
```

### Package `__init__.py`

Expose your classes in the package's `__init__.py` and guard against missing `lerobot`:

```python
# __init__.py
"""Custom policy package for LeRobot."""

try:
    import lerobot  # noqa: F401
except ImportError:
    raise ImportError(
        "lerobot is not installed. Please install lerobot to use this policy package."
    )

from .configuration_my_policy import MyPolicyConfig
from .modeling_my_policy import MyPolicy
from .processor_my_policy import make_my_policy_pre_post_processors

__all__ = [
    "MyPolicyConfig",
    "MyPolicy",
    "make_my_policy_pre_post_processors",
]
```

### Install and use

```bash
cd lerobot_policy_my_policy
pip install -e .

# Or install from PyPI if published
pip install lerobot_policy_my_policy
```

Once installed, your policy automatically integrates with LeRobot's training and evaluation tools:

```bash
lerobot-train \
    --policy.type my_policy \
    --env.type pusht \
    --steps 200000
```

---

## Path B: Contributing in-tree

When your policy has stabilized and there's clear value in shipping it with the library, you can land it directly in LeRobot. Read the general [contribution guide](./contributing) and the [PR template](https://github.com/huggingface/lerobot/blob/main/.github/PULL_REQUEST_TEMPLATE.md) first — that's where you'll find the testing/quality expectations every PR has to meet (`pre-commit run -a`, `pytest`, the community-review rule, etc.). What's below is the policy-specific layer on top of that.

### In-tree layout

```
src/lerobot/policies/my_policy/
├── __init__.py                    # re-exports config + modeling + processor factory
├── configuration_my_policy.py     # MyPolicyConfig + @register_subclass
├── modeling_my_policy.py          # MyPolicy(PreTrainedPolicy)
├── processor_my_policy.py         # make_my_policy_pre_post_processors
└── README.md                      # symlink → ../../../../docs/source/policy_my_policy_README.md
```

Two notes:

- The `README.md` next to the source is a **symlink** into `docs/source/policy_<name>_README.md` — the actual file lives under `docs/`. Existing policies (act, smolvla, diffusion, …) all do this; copy one of those symlinks. The policy README is conventionally minimal: paper link + BibTeX citation.
- The user-facing tutorial — what to install, how to train, hyperparameters, benchmark numbers — lives separately at `docs/source/<my_policy>.mdx` and is registered in `_toctree.yml` under "Policies".

The file names are load-bearing: the factory does lazy imports by name, and the processor is discovered by the `make_<policy_name>_pre_post_processors` convention.

### Wiring

Three places need to know about your policy. All by name.

1. **`policies/__init__.py`** — re-export `MyPolicyConfig` and add it to `__all__`. **Don't** re-export the modeling class; it loads lazily through the factory (so `import lerobot` stays fast).
2. **`factory.py:get_policy_class`** — add a branch returning `MyPolicy` from a lazy import.
3. **`factory.py:make_policy_config`** and **`factory.py:make_pre_post_processors`** — same idea, two more branches.

Mirror an existing policy that's structurally similar to yours; the diff is small.

### Heavy / optional dependencies

Most policies need a heavy backbone (transformers, diffusers, a specific VLM SDK). The convention is **two-step gating**: a `TYPE_CHECKING`-guarded import at module top, and a `require_package` runtime check in the constructor. [`modeling_diffusion.py`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/policies/diffusion/modeling_diffusion.py) is the canonical reference:

```python
from typing import TYPE_CHECKING
from lerobot.utils.import_utils import _diffusers_available, require_package

if TYPE_CHECKING or _diffusers_available:
    from diffusers.schedulers.scheduling_ddim import DDIMScheduler
else:
    DDIMScheduler = None  # keeps the symbol bindable at import time

class DiffusionPolicy(PreTrainedPolicy):
    def __init__(self, config):
        require_package("diffusers", extra="diffusion")
        super().__init__(config)
        ...
```

This way:

- `import lerobot.policies` keeps working without the extra installed (the symbol is just bound to `None`).
- Type checkers see the real symbol.
- Instantiating the policy without the extra raises a clear `ImportError` pointing at `pip install 'lerobot[diffusion]'`.

Add a matching extra to [`pyproject.toml`](https://github.com/huggingface/lerobot/blob/main/pyproject.toml) `[project.optional-dependencies]` and include it in the `all` extra so `pip install 'lerobot[all]'` keeps installing everything.

### Benchmarks and a published checkpoint

A new policy is much easier to review — and far more useful — when it ships with a working checkpoint and at least one number you can reproduce.

**Pick at least one in-tree benchmark.** LeRobot ships sim benchmarks with per-benchmark Docker images (LIBERO, LIBERO-plus, Meta-World, RoboTwin 2.0, RoboCasa365, RoboCerebra, RoboMME, VLABench and more). Pick the one that matches your policy's modality — VLAs usually go to LIBERO or VLABench; image-only BC to LIBERO or Meta-World. The full list lives under [Benchmarks](./libero) in the docs sidebar.

**Push the checkpoint & processors** to the Hub under `lerobot/<policy>_<benchmark>` (or your namespace if you don't have write access; a maintainer can mirror it). Use `PreTrainedPolicy.push_model_to_hub` so the repo gets `config.json`, `model.safetensors`, and a model card.

**Report results in your policy's MDX**, with the exact `lerobot-eval` command and hardware so anyone can re-run:

```markdown
## Results

Evaluated on LIBERO with `lerobot/<policy>_libero`:

| Suite          | Success rate | n_episodes |
| -------------- | -----------: | ---------: |
| libero_spatial |        87.5% |         50 |
| libero_object  |        93.0% |         50 |
| libero_goal    |        81.5% |         50 |
| libero_10      |        62.0% |         50 |
| **average**    |    **81.0%** |        200 |

Reproduce: `lerobot-eval --policy.path=lerobot/<policy>_libero --env.type=libero --env.task=libero_spatial --eval.n_episodes=50` (1× A100 40 GB).
```

Use `n_episodes ≥ 50` per suite for stable success-rate estimates.

If your policy is real-robot-only and no sim benchmark applies, swap the sim eval for: a public training dataset on the Hub, the `lerobot-train` command, the checkpoint, and a real-robot success rate over ≥10 episodes via `lerobot-rollout --policy.path=...`.

### PR checklist

The general expectations are in [`CONTRIBUTING.md`](https://github.com/huggingface/lerobot/blob/main/CONTRIBUTING.md) and the [PR template](https://github.com/huggingface/lerobot/blob/main/.github/PULL_REQUEST_TEMPLATE.md). On top of those, reviewers will look for:

- [ ] `MyPolicy` and `MyPolicyConfig` cover the surface above; `__init_subclass__` accepts the class.
- [ ] `factory.py` and `policies/__init__.py` are wired (lazy imports for modeling).
- [ ] `make_my_policy_pre_post_processors` follows the naming convention.
- [ ] Optional deps live behind a `[project.optional-dependencies]` extra and the `TYPE_CHECKING + require_package` guard.
- [ ] `tests/policies/` updated; backward-compat artifact committed & policy-specific tests.
- [ ] `src/lerobot/policies/<name>/README.md` symlinked into `docs/source/policy_<name>_README.md`; user-facing `docs/source/<name>.mdx` written and added to `_toctree.yml`.
- [ ] At least one reproducible benchmark eval in the policy MDX with a published checkpoint (sim benchmark, or real-robot dataset + checkpoint).

The fastest way to get a clean PR is to copy the directory of the existing policy closest to yours, rename, and replace contents method by method. Don't wait until everything is polished — open a draft PR early and iterate with us; reviewers would much rather give feedback on a half-finished branch than a fully-merged one.

---

## Examples and community contributions

Check out these example policy implementations:

- [DiTFlow Policy](https://github.com/danielsanjosepro/lerobot_policy_ditflow) — Diffusion Transformer policy with flow-matching objective. Try it out in this example: [DiTFlow Example](https://github.com/danielsanjosepro/test_lerobot_policy_ditflow)

Thanks for taking the time to bring a new policy into LeRobot. Every architecture that lands in `main` — and every plugin published by the community — makes the library a little more useful for the next person, and a little more representative of where robot learning is going. We're looking forward to seeing what you ship. 🤗