ManiLadder PI0.5 LoRA models
single_task
One PI0.5 LoRA checkpoint per ManiLadder task (60 tasks), each finetuned on that task's 20 demos. For every task, all saved checkpoints (steps 5kโ40k, every 5k) were re-evaluated for 50 episodes with fixed episode seeds 1000โ1049 (identical across checkpoints of a task), and the checkpoint with the highest success rate is published here (ties โ earliest step).
Each single_task/<task>/ folder contains:
lora_step_XXXXXXX.npzโ LoRA + trainable weightsnorm_stats.jsonโ normalization statistics used in trainingeval_result.jsonโ 50-episode evaluation of this checkpoint
single_task/results.csv lists the selected checkpoint per task; single_task/all_checkpoints_eval.csv has the
50-episode result of every evaluated checkpoint (477 total).
Evaluation: exec_steps=16, sample_steps=10. Tasks whose checkpoints all scored 0/50 are still included;
for them the step choice is arbitrary.
| task | level | step | success (50 ep) |
|---|---|---|---|
| DualArmButtonPress-v1 | 1 | 5000 | 0.98 |
| DualArmCoverCloth-v1 | 1 | 15000 | 0.80 |
| DualArmFoldHandKerchief-v1 | 1 | 5000 | 0.74 |
| DualArmOpenPen-v1 | 1 | 35000 | 0.36 |
| DualArmRopeCylinderWarpping-v1 | 1 | 10000 | 0.62 |
| DualArmRopeStretch-v1 | 1 | 10000 | 0.92 |
| GraspCylinder-v1 | 1 | 15000 | 0.94 |
| LiftBucket-v1 | 1 | 40000 | 0.96 |
| OpenDoor-v1 | 1 | 5000 | 0.30 |
| PickPlacePen-v1 | 1 | 20000 | 0.36 |
| PushSoccer-v1 | 1 | 40000 | 0.80 |
| RopePalmCageHoldDex-v1 | 1 | 5000 | 0.94 |
| TurnOnFaucet-v1 | 1 | 10000 | 0.92 |
| ClothWipe-v1 | 2 | 25000 | 0.52 |
| DualArmClothAlign-v1 | 2 | 40000 | 0.38 |
| DualArmOpenBottle-v1 | 2 | 30000 | 0.06 |
| DualArmOpenLaptop-v1 | 2 | 25000 | 0.42 |
| DualArmPegInHole-v1 | 2 | 5000 | 0.18 |
| DualArmPlaceRopeOverRod-v1 | 2 | 40000 | 0.46 |
| DualArmStuffCloth-v1 | 2 | 15000 | 0.40 |
| DualArmThrowBlock-v1 | 2 | 5000 | 0.00 |
| FoldShirt-v1 | 2 | 40000 | 0.72 |
| GraspTwoBlocks-v1 | 2 | 5000 | 0.72 |
| HammerNailOut-v1 | 2 | 40000 | 0.44 |
| HangMug-v1 | 2 | 10000 | 0.70 |
| KitAssembly-v1 | 2 | 15000 | 0.06 |
| PivotBook-v1 | 2 | 15000 | 0.38 |
| ReorientPen-v1 | 2 | 25000 | 0.38 |
| RollingPin-v1 | 2 | 25000 | 0.96 |
| StraightenTwoRopesSequential-v1 | 2 | 15000 | 0.36 |
| DualArmOpenFridge-v1 | 3 | 5000 | 0.00 |
| DualArmPingpongBalance-v1 | 3 | 15000 | 0.20 |
| DualArmSetupTable-v1 | 3 | 25000 | 0.04 |
| DualArmShapeDoll-v1 | 3 | 30000 | 0.04 |
| DualArmThreadRopeThroughTube-v1 | 3 | 35000 | 0.16 |
| DualArmWeaveCloth-v1 | 3 | 20000 | 0.32 |
| HammerNail-v1 | 3 | 35000 | 0.12 |
| HitBox-v1 | 3 | 25000 | 0.06 |
| LiquidMeasuring-v1 | 3 | 35000 | 0.32 |
| MobilePickPlace-v1 | 3 | 15000 | 0.08 |
| Stack6Blocks-v1 | 3 | 5000 | 0.00 |
| TweezersPickPlace-v1 | 3 | 5000 | 0.00 |
| BuildTent-v1 | 4 | 10000 | 0.06 |
| DualArmBallClassify-v1 | 4 | 10000 | 0.00 |
| DualArmBilliardBridge-v1 | 4 | 5000 | 0.00 |
| DualArmClothHanger-v1 | 4 | 5000 | 0.00 |
| DualArmFlipTable-v1 | 4 | 5000 | 0.00 |
| DualArmJumpRope-v1 | 4 | 20000 | 0.02 |
| DualArmKeyboardType-v1 | 4 | 5000 | 0.00 |
| DualArmMahjongSetup-v1 | 4 | 5000 | 0.02 |
| DualArmSendPingpong-v1 | 4 | 40000 | 0.08 |
| DualArmShootBasketball-v1 | 4 | 5000 | 0.00 |
| FitnessBall-v1 | 4 | 5000 | 0.00 |
| FlipPan-v1 | 4 | 40000 | 0.04 |
| HitBilliard-v1 | 4 | 5000 | 0.00 |
| PingPongBallTransport-v1 | 4 | 40000 | 0.16 |
| RingTossing-v1 | 4 | 5000 | 0.00 |
| RodThroughHoles-v1 | 4 | 5000 | 0.02 |
| SpinPenHora-v1 | 4 | 5000 | 0.00 |
| TennisRally-v1 | 4 | 15000 | 0.06 |
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support