Downloads · 30 days
0
rlinf-libero-chunk8-cnn-bc
jacob3333/rlinf-libero-chunk8-cnn-bc
rlinf-libero-chunk8-cnn-bc is a robotics model from jacob3333. Use it for the robotics task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Two pretrained (behavior-cloned) image-only, action-chunk-8 CNN policies for LIBERO-spatial task 1, distilled from π0 rollouts (std-0.10 action head). These are the warm-start policies behind the WAN world-model PPO r…
Access
Public
Updated Jul 7, 2026
Repo size
55.2 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt55.2 MB · 100%
At a glance
- Task
- Robotics
- License
- mit
- Access
- Public
- Created
- Jul 7, 2026
- Updated
- Jul 7, 2026
- SHA
- 160fd874
Model card
From the Hugging Face model README
RLinf — LIBERO-spatial image-only chunk-8 CNN BC policies
Two pretrained (behavior-cloned) image-only, action-chunk-8 CNN policies for LIBERO-spatial task 1, distilled from π0 rollouts (std-0.10 action head). These are the warm-start policies behind the WAN world-model PPO results in RLinf (stage-3 WM RL + JEPA-consistency pessimism).
| file | strength (fixed 48-ep eval) | role |
|---|---|---|
weak4_t1_chunk8_std010.pt | ~0.40 (weak, 4 demos) | the weak base for the "does RL/pessimism help a weak policy" WAN-PPO experiments |
libero_spatial_t1_bc_pi0_imageonly_chunk8_std010.pt | the strong base for the WAN-PPO / pessimism results |
Both are plain PyTorch state_dicts that strict-load into the RLinf cnn_policy with
num_action_chunks=8 (image-only, actor_logstd = ln(0.10)).
Usage
hf download jacob3333/rlinf-libero-chunk8-cnn-bc --local-dir checkpoints/bc --include "*.pt"
The RLinf configs (wan_libero_spatial_t1_ppo_cnn.yaml and its sole/consistency variants) load the
strong one as runner.ckpt_path; the weak runs override with weak4_t1_chunk8_std010.pt.
- Task
- Robotics
- License
- mit
- Created
- Jul 7, 2026
- Updated
- Jul 7, 2026