rlt
Datasets
All datasets matching “rlt”rlt-maniskill-PegInsertionSide-v1-400-succ
RLT ManiSkill Joint
Dataset Summary
rlt_maniskill_joint is a LeRobot-style dataset for joint-control Robot Learning Token (RLT) training on the ManiSkill peg insertion task.
It is designed for the RLinf + OpenPI pi05_rlt_joint pipeline and is used in three stages:
OpenPI supervised fine-tuning (SFT) base policy training
RLT Stage 1 RL-token training
RLT Stage 2 online RL initialization and normalization
The dataset corresponds to the ManiSkill task:… See the full description on the dataset page: https://huggingface.co/datasets/RLinf/rlt-maniskill-PegInsertionSide-v1-400-succ.yam_lego_taxi_s200_rlt_annotrltr-datasmolvla-rlt
SmolVLA-RLT: PegInsertionSide-v1 (three cameras)
Successful motion-planning demonstrations replayed from saved ManiSkill states. Every 20 FPS observation provides 512×512 RGB from environment_camera, hand_camera, and insertion_camera. The insertion camera is mounted in the peg frame with its reference at the red insertion end. Actions are 8D absolute pd_joint_pos commands; observation.state is 9D Panda qpos. Exact source and camera-config hashes are in render_manifest.json.
contashasum crazyflie-scale.glb
4be1c223bb268e35163f98daa675a60a6b2876c2 crazyflie-scale.glb
mv crazyflie-scale.glb 4be1c223bb268e35163f98daa675a60a6b2876c2
const res = await fetch("https://huggingface.co/datasets/rl-tools/conta-data/resolve/main/<sha>");
rlt-realworld-ee-peginsertion-100-succ