---
license: mit
library_name: pytorch
tags:
  - robotics
  - reinforcement-learning
  - world-model
  - manipulation
  - mujoco
---

# SuperMimic manipulation checkpoints

Trained SuperMimic agents for three simulated ARX5 manipulation tasks from
[supermimic_manipulation](https://github.com/emoPointer/supermimic_manipulation). Each
checkpoint is taken at 4,000 training iterations and holds the full agent: world model,
actor, critic, observation normalizers and optimizer states. It can be evaluated directly or
used to continue training.

| Task | Held-out success | Per reset category 0 / 1 / 2 / 3 | Training time |
| --- | --- | --- | --- |
| `lemon` | 100.0% | 100 / 100 / 100 / 100 | 1.8 h |
| `box_in_bin` | 94.9% | 97 / 91 / 95 / 97 | 1.9 h |
| `mug_hang` | 96.9% | 94 / 98 / 95 / 100 | 2.8 h |

Success is the simulator's native task success over 256 complete episodes per task (64 per
reset category) on the held-out reset banks in
[emopointer/supermimic-manipulation-reset-banks](https://huggingface.co/datasets/emopointer/supermimic-manipulation-reset-banks).
Training used one NVIDIA A100-SXM4-80GB per run.

## Files

```text
<task>/model_004000.pt     # agent checkpoint
<task>/params/env.yaml     # training environment; evaluation checks it against the current one
<task>/params/agent.yaml   # SuperMimic hyperparameters
<task>/params/mdp.json     # world-model state, action and imagined-reward contract
<task>/params/runtime.json # training run settings and reset-bank provenance
```

Keep each `params/` directory next to its checkpoint: `clab eval policy` reads
`<task>/params/env.yaml` from there.

## Usage

```bash
hf download emopointer/supermimic-manipulation --local-dir checkpoints
hf download emopointer/supermimic-manipulation-reset-banks --repo-type dataset --local-dir banks
clab eval policy --task box_in_bin --algorithm supermimic \
  --checkpoint checkpoints/box_in_bin/model_004000.pt \
  --reset-bank banks/box_in_bin_test.pt --episodes-per-type 64 --num-envs 64 \
  --seeds 100000 --split-label held_out --cuda-graph-mode plain \
  --output reports/box_in_bin.json
```

See the repository README for installation, the approach and the references (SuperMimic,
arXiv:2610.28480; OmniReset, ICLR 2026).