1 CounterfactualPoseGeneratorConfig

pose_generation.CounterfactualPoseGeneratorConfig()

Configuration for multi-step finite-candidate rollout generation.

Candidate sampling stays in pose_generation: each rollout step regenerates a shell from the current pose/history, applies hard validity masks, and selects valid actions by the configured policy. Persistence, source-row lineage, and Q_H replay views are owned by aria_nbv.rollouts.

1.1 Attributes

Name	Description
robust_temperature_logits	Normalize temperature-softmax scores by median/IQR before applying temperature.

# CounterfactualPoseGeneratorConfig { #aria_nbv.pose_generation.CounterfactualPoseGeneratorConfig }

```python
pose_generation.CounterfactualPoseGeneratorConfig()
```

Configuration for multi-step finite-candidate rollout generation.

Candidate sampling stays in `pose_generation`: each rollout step regenerates
a shell from the current pose/history, applies hard validity masks, and
selects valid actions by the configured policy. Persistence, source-row
lineage, and `Q_H` replay views are owned by `aria_nbv.rollouts`.

## Attributes

| Name | Description |
| --- | --- |
| [robust_temperature_logits](#aria_nbv.pose_generation.CounterfactualPoseGeneratorConfig.robust_temperature_logits) | Normalize temperature-softmax scores by median/IQR before applying temperature. |