---
library_name: lerobot
pipeline_tag: robotics
tags: [act, lerobot, robotics, dg5f, ur5e, gelsight, ablation]
---

# ACT — blue 186ep, GelSight no gelsight

One point of a GelSight-resolution sweep on the DG-5F + UR5e blue-cable task.
Runs differ only in GelSight resolution, so any gap between them is attributable
to tactile resolution alone.

- **Dataset**: [Kaz55/dg5f_ur5e_blue_180ep_gs0](https://huggingface.co/datasets/Kaz55/dg5f_ur5e_blue_180ep_gs0) — 186 episodes / 186,152 frames
- **GelSight**: no gelsight
- **RealSense**: 640x480 (identical across the sweep)
- **Policy**: ACT, chunk_size=60, n_action_steps=60
- **Training**: 100,000 steps (~4.3 epochs), batch 8, seed 1000

## Inputs

`observation.state` (26) + RealSense x2

`observation.velocity` and `observation.effort` are present in the dataset but
**deliberately excluded**. Feature auto-derivation would otherwise feed them to
the policy, adding a second difference between runs and breaking the ablation.

## Sweep (186 episodes)

| GelSight | model |
|---|---|
| 500x375 | act-blue-180ep-gs500-ac60 |
| 320x240 | act-blue-180ep-gs320-ac60 |
| 160x120 | act-blue-180ep-gs160-ac60 |
| 88x66 | act-blue-180ep-gs88-ac60 |
| none | act-blue-180ep-gs0-ac60 |

## Caveat

On the related 180-episode `combined` sweep, final training loss was 0.118 across
*every* resolution **including no-GelSight-at-all** — training loss did not detect
the tactile input. Treat these numbers as a sanity check, not as evidence that
tactile resolution matters; that requires on-robot evaluation.