# FetchPush-v4 goal-directed push: robotics skill example

FetchPush-v4 goal-directed push. Source-pinned, bounded simulation with explicit goal checks; no physical execution.

## Task and environment

gymnasium-robotics | 1.4.2 | fetch | cartesian_delta_feedback | linux | 3.10

## Example input

```json
{
  "seed": 0
}
```

## Retrieve and prepare

Read https://hub.superfastrobotics.com/skills/gymrobotics-fetchpush-v4/skill.json or https://api.superfastrobotics.com/v1/skills/gymrobotics-fetchpush-v4?hub_commit=ede75c00118e9808e5099da43c26f4619cc3bc37&record_version=1.0.0&include=experience without installing a client. Inspect the license, exact environment and evidence before preparation. Preparation and execution remain separate.

Source: https://github.com/Farama-Foundation/Gymnasium-Robotics at 42eae53b2b27321d29090c219ce2f675c596de77. Record version: 1.0.0.

## Success condition

All declared goal and finite-state checks pass; exit 0 with task_complete. Native environment success flag after bounded closed-loop control; object/state coordinates are never teleported after reset.

## Recorded evidence

task_complete: All 3 frozen cases completed against this exact adapter and source.

This page is a data-only example and performs no execution.