Embodied · action_chunking_policy · robot_policy · imitation_policy · policy_rollout
Action Chunking Transformer
tonyzhaozh
The ACT policy, DETR-VAE, transformer, ResNet backbone, preprocessing, and action-chunk aggregation execute from the flattened in-tree package.
Build your run
Choose a recorded variant, then copy the exact setup or inspection command.
worldfoundry-eval evaluate \
--mode model \
--model-id act \
--model-runner worldfoundry:pipeline \
--model-manifest-dir worldfoundry/data/models/catalog \
--requests-path tmp/requests.jsonl \
--output-dir tmp/model_eval/act \
--metric artifact_count \
--jsonCompatibility & versions
Manifest-backed recipe
- Integration
- integrated
- Runner evidence
- Not recorded
- Environment
- worldfoundry-act
- Python
- 3.10
- CUDA
- Cu118 Or Newer
- PyTorch
- torch
- Source revision
- —
- Checkpoint revision
- —
- Runtime profile
- act
- Pipeline binding
- act
- Runner
- worldfoundry.pipeline
- Pipeline target
- worldfoundry.pipelines.component_pipelines:ACTPipeline
- Backend stage
- in_tree_runtime
- Runtime status
- in_tree_checkpoint_runtime_local_assets_required
- Driver status
- checkpoint_runtime_ready
- Environment kind
- Dedicated environment
Install environment
The environment resolver reads the recorded profile and chooses the unified or dedicated environment shown here.
bash scripts/setup/model_env_install.sh --model actPackage constraints 4
numpyPillowtorchtorchvision
Conda packages 2
pythonpip
Checkpoints & assets
Run the local check before allocating compute. Gated, private, and license fields below come directly from the checkpoint manifest.
worldfoundry-eval zoo model-download --model-id act --check-local --jsonNo checkpoint repository is recorded in the catalog manifest.
Launch & outputs
The generated command uses the shared evaluation boundary and writes durable result manifests and artifacts.
worldfoundry-eval evaluate \
--mode model \
--model-id act \
--model-runner worldfoundry:pipeline \
--model-manifest-dir worldfoundry/data/models/catalog \
--requests-path tmp/requests.jsonl \
--output-dir tmp/model_eval/act \
--metric artifact_count \
--jsonInput contract
| Field | Recorded contract |
|---|---|
actions | action_chunk, proprio, action_space |
image | Required |
instruction | Required |
prompt | Optional |
video | Optional |
Artifact contract
| Artifact kind | Filename / path |
|---|---|
action_trace | act_action_trace.json |
Evidence & sources
Catalog integration, native-demo parity, and runner parity are independent records.
- Integration
- integrated
- Runner evidence
- Not recorded
- Native demo evidence
- Not recorded
- Validation imports
- numpy, PIL, torch, torchvision
worldfoundry/data/models/catalog/vla_va_wam/act.yamlGitHubhttps://github.com/tonyzhaozh/act



