---
title: "Action Chunking Transformer"
description: "ALOHA ACT: DETR-VAE emits a 50-step bimanual chunk; WorldFoundry runs inference in-tree and does not ship a checkpoint."
modelId: "act"
pageSource: authored
---

ACT (Action Chunking Transformer) is the ALOHA imitation policy: instead of one joint target per step, it emits a short horizon of future actions so control stays smooth. At test time the CVAE encoder is dropped and the style latent is the prior mean (zero). The official paper is [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://arxiv.org/abs/2304.13705) (arXiv 2304.13705). The project page is [tonyzhaozh.github.io/aloha](https://tonyzhaozh.github.io/aloha/). The GitHub tree is [tonyzhaozh/act](https://github.com/tonyzhaozh/act).

<ModelPaperFigures modelId="act" locale="en" />

WorldFoundry keeps the full inference stack — DETR-VAE, transformer encoder-decoder, ResNet-18 backbone, preprocessing, and temporal aggregation — under `worldfoundry/synthesis/action_generation/act`. There is **no catalog variant and no official weight file**. Checkpoint-backed `predict_action` is implemented; it stays gated on a caller-staged `policy_best.ckpt` plus matching `dataset_stats.pkl`. Static and CPU contract checks pass. Alias `action-chunking-transformer` resolves here.

<ModelCommandBuilder modelId="act" locale="en" />

## What it is for

Use ACT as a fixed-embodiment **action-chunking** baseline — not an open-vocabulary VLA. Recorded inputs are RGB (`image`) and `instruction`; `prompt` is unused. The pipeline is `ACTPipeline`; the artifact is `act_action_trace.json`. The natural local target in this catalog is a scripted sim transfer-cube policy you train or stage yourself, then replay against held-out demonstrations.

This is the page for runner parity, checkpoint staging, and the chunk contract before you move to larger language-conditioned stacks.

## Runtime contract

In-tree defaults (not a downloaded checkpoint):

- Cameras: `cam_head`, `cam_right_wrist`, `cam_left_wrist`
- Proprioception: **`state_dim` 14** (two 7-DoF arms)
- **`chunk_size` 50**, `temporal_agg=true`, backbone **ResNet-18**
- Transformer: 4 encoder / 7 decoder layers, hidden 512, 8 heads

The paper’s ALOHA hardware write-up uses four 480×640 cameras at 50 Hz and discusses a 90-step real-robot chunk. That is upstream hardware, not the WorldFoundry config above. Actions are an `action_chunk` plus proprio / action-space metadata.

Stage weights here:

`${WORLDFOUNDRY_CKPT_DIR}/embodied_action/act/sim_transfer_cube_scripted/policy_best.ckpt`

plus the matching `dataset_stats.pkl` beside it. PyTorch loads with `weights_only=true` and strict keys. Stats use a NumPy-only reader — no upstream pickle execution.

## Running in WorldFoundry

Dedicated environment `worldfoundry-act` (Python 3.10, CUDA 11.8 or newer). No package or checkpoint is downloaded at runtime. After staging:

```
worldfoundry-eval run act
```

No license is recorded in this repository. Confirm the upstream ACT / ALOHA terms before production use.

<ModelRelatedRecipes modelId="act" locale="en" />