Section 21.5: Sources of demonstrations: humans, planners, foundation models

A Careful Control Loop

This section develops the technical contract for sources of demonstrations: humans, planners, foundation models into a usable mental model. First we define the object of study, then we connect it to the agent loop, then we test it with a compact implementation.

The key question in Sources of demonstrations: humans, planners, foundation models is practical: what must the agent know, what can it observe, what action is available, and what evidence shows that the action worked under the stated conditions?

Theory

For Sources of demonstrations: humans, planners, foundation models, the practical design rule is to make the interface inspectable before optimization begins: inputs, outputs, units, latency, bounds, and failure labels should all be visible in the saved artifact.

Worked Example

For Sources of demonstrations: humans, planners, foundation models, keep one concrete rollout in view. A sensor reading becomes an estimate, the estimate constrains an action, the action changes the world, and the next observation confirms or contradicts the assumption. The section's idea is useful only if it improves that loop.

from pathlib import Path

dataset_root = Path("robot_demos")
for episode in sorted(dataset_root.glob("episode_*")):
    print("inspect", episode.name)
print("next step: convert demonstrations to the LeRobotDataset format")

Expected output: the printed trace for Sources of demonstrations: humans, planners, foundation models should expose the method configuration, the measured evidence field, and the failure label. If one of those fields is missing or unchanged under the perturbation, the example is not yet an evaluation artifact.

# Score demonstration sources for a contact-rich tabletop task.
# Higher scores mean better match to hardware, coverage, and auditability.
sources = {
    "human_teleop": {"hardware": 3, "coverage": 2, "audit": 2},
    "planner_sim": {"hardware": 1, "coverage": 3, "audit": 3},
    "foundation_model": {"hardware": 1, "coverage": 3, "audit": 1},
}
for source, scores in sources.items():
    total = sum(scores.values())
    print(source, total, scores)

Practical Recipe

1. Write the observation, action, and success metric before choosing a model.
2. Build a baseline that is simple enough to debug by inspection.
3. Add the library implementation only after the baseline behavior is understood.
4. Record failures as structured cases: perception error, state error, planning error, control error, or evaluation error.
5. Run at least one perturbation test before trusting the result.

Sources of demonstrations: humans, planners, foundation models becomes useful when it is tied to a closed-loop contract. In this Part V section on Sources of demonstrations: humans, planners, foundation models, the contract names the observation stream, the state estimate, the action representation, the timing budget, and the evaluation artifact. Without that contract, a model can look capable in a notebook while failing the first time a sensor drops a frame or a controller saturates.

For Sources of demonstrations: humans, planners, foundation models, separate the conceptual claim, the systems claim, and the evidence claim. A plausible mechanism, a clean interface, and a closed-loop result are different claims; the section should keep their evidence separate.

For Sources of demonstrations: humans, planners, foundation models, start with a small baseline that logs inputs, outputs, units, timestamps, and termination conditions before moving to Gymnasium or PettingZoo. The library run should keep the same artifact schema, so the comparison remains a same-task evaluation.

1. Write a one-paragraph task contract with observation, action, success, and failure fields.
2. Start with the smallest simulator, dataset, or wrapper that exposes the task contract faithfully.
3. Run one deterministic smoke test and one perturbation test before scaling.
4. Save a single result artifact containing configuration, seed, metrics, videos or traces, and failure labels.
5. Compare methods only when one script evaluates them on the same task panel.

When Sources of demonstrations: humans, planners, foundation models fails, avoid labeling the whole method as weak. First assign the failure to perception, state estimation, planning, control, timing, data coverage, or evaluation. Then rerun one controlled perturbation that isolates the suspected cause. This pattern turns a disappointing rollout into a reusable diagnostic asset.