Add API Examples (#2289)

* (unscrewing things up) (#2288)

* fix: expose a function explicitly building a frame for inference

* fix: first make dataset frame, then make ready for inference

* fix: reducing reliance on lerobot record for policy's ouptuts too

* fix: encapsulating squeezing out + device handling from predict action

* fix: remove duplicated call to build_inference_frame and add a function to only perform data type handling (whole conversion is: keys matching + data type conversion)

* refactor(envs): add custom-observation-size (#2167)

* fix: add MockMotorBus to MockRobot

* rl: first drafts

* add: all components of HIL SERL

* fix: actor block works

* fix: less friction, less friction

* add: hil-serl complete example

* fix: dataset names

* fix: restructuring example folder

* fix: act works but found bug in how ACT works

* fix: same path for both pre and postprocessors

* fix: paths

* add: example usage for act

* add: using ACT example

* fix: training examples

* fix: using examples

* fix: camera index

* fix: rename workflows into tutorial so that the path of the files is lerobot/examples/tutorial/...

* fix: upload everything in one repo

* fix: model name

* fix: simplify model path

* add: VLAs example

---------

Signed-off-by: Francesco Capuano <74058581+fracapuano@users.noreply.github.com>

* fix: minor fix using named attributes

* fix: change model to act

* fix: named attributes for inference frame building

* fix: minor fixes to smolvla

* fix: small changes to pi0

* remove: old file that should have never been committed (ups sorry sorry)

---------

Signed-off-by: Francesco Capuano <74058581+fracapuano@users.noreply.github.com>

examples/tutorial/act/act_training_example.py

@@ -0,0 +1,98 @@
+"""This script demonstrates how to train ACT Policy on a real-world dataset."""
+
+from pathlib import Path
+
+import torch
+
+from lerobot.configs.types import FeatureType
+from lerobot.datasets.lerobot_dataset import LeRobotDataset, LeRobotDatasetMetadata
+from lerobot.datasets.utils import dataset_to_policy_features
+from lerobot.policies.act.configuration_act import ACTConfig
+from lerobot.policies.act.modeling_act import ACTPolicy
+from lerobot.policies.factory import make_pre_post_processors
+
+
+def make_delta_timestamps(delta_indices: list[int] | None, fps: int) -> list[float]:
+    if delta_indices is None:
+        return [0]
+
+    return [i / fps for i in delta_indices]
+
+
+output_directory = Path("outputs/robot_learning_tutorial/act")
+output_directory.mkdir(parents=True, exist_ok=True)
+
+# Select your device
+device = torch.device("mps")  # or "cuda" or "cpu"
+
+dataset_id = "lerobot/svla_so101_pickplace"
+
+# This specifies the inputs the model will be expecting and the outputs it will produce
+dataset_metadata = LeRobotDatasetMetadata(dataset_id)
+features = dataset_to_policy_features(dataset_metadata.features)
+
+output_features = {key: ft for key, ft in features.items() if ft.type is FeatureType.ACTION}
+input_features = {key: ft for key, ft in features.items() if key not in output_features}
+
+cfg = ACTConfig(input_features=input_features, output_features=output_features)
+policy = ACTPolicy(cfg)
+preprocessor, postprocessor = make_pre_post_processors(cfg, dataset_stats=dataset_metadata.stats)
+
+policy.train()
+policy.to(device)
+
+# To perform action chunking, ACT expects a given number of actions as targets
+delta_timestamps = {
+    "action": make_delta_timestamps(cfg.action_delta_indices, dataset_metadata.fps),
+}
+
+# add image features if they are present
+delta_timestamps |= {
+    k: make_delta_timestamps(cfg.observation_delta_indices, dataset_metadata.fps) for k in cfg.image_features
+}
+
+# Instantiate the dataset
+dataset = LeRobotDataset(dataset_id, delta_timestamps=delta_timestamps)
+
+# Create the optimizer and dataloader for offline training
+optimizer = cfg.get_optimizer_preset().build(policy.parameters())
+batch_size = 32
+dataloader = torch.utils.data.DataLoader(
+    dataset,
+    batch_size=batch_size,
+    shuffle=True,
+    pin_memory=device.type != "cpu",
+    drop_last=True,
+)
+
+# Number of training steps and logging frequency
+training_steps = 1
+log_freq = 1
+
+# Run training loop
+step = 0
+done = False
+while not done:
+    for batch in dataloader:
+        batch = preprocessor(batch)
+        loss, _ = policy.forward(batch)
+        loss.backward()
+        optimizer.step()
+        optimizer.zero_grad()
+
+        if step % log_freq == 0:
+            print(f"step: {step} loss: {loss.item():.3f}")
+        step += 1
+        if step >= training_steps:
+            done = True
+            break
+
+# Save the policy checkpoint, alongside the pre/post processors
+policy.save_pretrained(output_directory)
+preprocessor.save_pretrained(output_directory)
+postprocessor.save_pretrained(output_directory)
+
+# Save all assets to the Hub
+policy.push_to_hub("fracapuano/robot_learning_tutorial_act")
+preprocessor.push_to_hub("fracapuano/robot_learning_tutorial_act")
+postprocessor.push_to_hub("fracapuano/robot_learning_tutorial_act")