learner1119/RLDX-1-FT-ffw-sh5
RLDX-1-FT-ffw-sh5
`RLWRLD/RLDX-1-PT` fine-tuned on the FFW-SH5 rev1 dual-arm / dual-hand robot.
Read this first. This is a pipeline smoke-test artifact, not a usable policy. It was trained on 7 episodes (1253 frames) for 10,000 steps at global batch 64 — roughly 510 epochs over the same handful of trajectories. It is heavily overfit by construction. It was produced to verify that training and inference run end to end on this robot's data, and it should not be taken as an indication of what RLDX-1 can do.
What it does
Predicts 16-step absolute joint-target chunks for both arms and both hands from a single head camera and the current joint state.
The robot's raw observation.state / action vectors are 57-dim; this model uses 54 of them. head_joint1/2 and lift_joint are excluded because they never move anywhere in the training data.
Actions are absolute joint targets (ActionRepresentation.ABSOLUTE, ActionType.NON_EEF), not deltas and not end-effector poses.
Known limitations
- Overfit. ~510 epochs over 7 episodes. Expect it to reproduce the training trajectories and generalize to nothing.
- The language conditioning is meaningless. The training dataset's
tasks.jsonlcontains the placeholder string"1611"— a task ID, not an instruction — so the model was conditioned on that literal string for every sample. It has no instruction-following ability. - Head camera only. Wrist cameras exist in the source data but were not used.
- Hands are weakly supervised. Only 2 of the 7 episodes move the fingers at all; the rest move the arms with the hands held fixed.
Evaluation
Open-loop, against ground-truth actions on held-in trajectories (there is no held-out split — the dataset is too small):
MAE 0.033 rad ≈ 1.9°. These are training trajectories, so the numbers measure fit, not generalization. Note also that the flow-matching sampler is not seeded: repeated evaluations of an unchanged checkpoint vary by roughly ±15%.
Peak inference VRAM at batch 1: 15.83 GiB (bf16, 6.9B parameters).
Usage
Requires the RLDX-1 codebase.
python rldx/eval/open_loop_eval.py \
--model-path learner1119/RLDX-1-FT-ffw-sh5 \
--dataset-path /path/to/ffw_sh5_0812 \
--embodiment-tag GENERAL_EMBODIMENT \
--traj-ids 1 2 --action-horizon 16 --steps 64Or serve it:
python rldx/eval/run_rldx_server.py --model-path learner1119/RLDX-1-FT-ffw-sh5Observation keys follow {modality}.{key}: video.cam_head, state.left_arm, state.right_arm, state.left_hand, state.right_hand, annotation.human.task_description.
No --modality-config-path is needed — the modality config is baked into the processor saved alongside these weights.
Training
Only the inference artifacts are published here (weights, processor, experiment config). The DeepSpeed optimizer state is not included, so this checkpoint can be used for inference or as a fine-tuning base, but not to resume the original run.
License
Licensed under the RLWRLD Model License v1.0 — see LICENSE.md for the full text.
This is a Derivative Model of RLWRLD/RLDX-1-PT. The license is non-commercial, requires attribution, and is share-alike: if you distribute a model derived from this one, it must carry these same terms. Section 3.5 additionally prohibits military, weapons, and non-consensual surveillance applications.