Downloads · 30 days
0
mlsbench-jepa-planning-ac-jepa-two-rooms
knightnemo/mlsbench-jepa-planning-ac-jepa-two-rooms
mlsbench-jepa-planning-ac-jepa-two-rooms is a reinforcement learning model from knightnemo. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
This repository hosts the pretrained AC Video JEPA checkpoint used for the jepa-planning task in MLS-Bench.
Access
Public
Updated Mar 19, 2026
Repo size
67.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.tar67.6 MB · 100%
At a glance
- Task
- Reinforcement Learning
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Mar 19, 2026
- Updated
- Mar 19, 2026
- SHA
- e5bda959
Model card
From the Hugging Face model README
MLS-Bench JEPA Planning Checkpoint
This repository hosts the pretrained AC Video JEPA checkpoint used for the jepa-planning task in MLS-Bench.
Contents
e-11.pth.tar: final epoch-11 checkpointlatest.pth.tar: latest checkpoint alias from the same runmetadata.json: release metadataSHA256SUMS.json: sha256 checksums for verification
Provenance
- Source repo:
Imbernoulli/MLS-Bench - Task branch/worktree commit:
19af17d99158a35c53782f8cc42a1b5cf3a985a1 - Task:
tasks/jepa-planning - Environment: Two Rooms
- Upload time (UTC): 2026-03-19T22:14:58.302746+00:00
Baseline metrics on this checkpoint
random: success_rate=0.40, mean_dist=19.5983, mean_steps_to_success=119.00cem: success_rate=0.60, mean_dist=12.1388, mean_steps_to_success=54.75mppi: success_rate=0.70, mean_dist=9.9821, mean_steps_to_success=64.14
SHA256
e-11.pth.tar:f5d015b66745d1de5352cf03dfe2fd537889d6f101e4e84bc50b9c17bca45abflatest.pth.tar:a3bf9ef879bf748e2742eccb1ac21d65acc5eeefc25ecddf66f7cc7d495eb9d3
Usage
Download either checkpoint and load it with torch.load(..., map_location=device, weights_only=False).
- Task
- Reinforcement Learning
- Library
- pytorch
- License
- mit
- Created
- Mar 19, 2026
- Updated
- Mar 19, 2026