ASEnv-tlabs/ASE
Train reusable motion control skills for physically simulated characters, using adversarial skill embeddings so one cont…
No ratings yet
Rate this skill
Stars1.1k
Forks152
Watchers1.1k
Open Issues43
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/nv-tlabs/ASE.git
OverviewOverview
Key Features
Train reusable motion control skills for physically simulated characters, using adversarial skill embeddings so one controller covers multiple motions instead of training each task from scratch. Key capabilities include: 1. Adversarial skill embedding: constrain the skill latent space with an adversarial discriminator so distinct motion skills are separable and composable in the embedding space, yielding a reusable low-level controller; 2. Physically simulated character control: train joint-level motion control for humanoid and other characters in a physics engine, producing policies that directly drive simulated characters; 3. Skill reuse and downstream fine-tuning: use pretrained skill embeddings as initialization for fast fine-tuning on downstream motion tasks, reducing repeated training cost.
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 1778 |
|---|---|
| Data source | GitHub |
| Repository | nv-tlabs/ASE |
| Category | AI & Machine Learning / Reinforcement Learning & Physics Simulation |
| Primary language | Python |
| License | Other |
| Default branch | main |
| GitHub repository ID | 485523585 |
| Node ID | R_kgDOHPCAgQ |
| Rank | #693 (position within the source ranking) |
| Site-wide popularity rank | #788 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now1,128
- Previous point · 09-29 1,125
- vs previous point +3
- 2 data points 12 days
- Now152
- Previous point · 09-29 151
- vs previous point +1
- 2 data points 12 days
TimelineTimeline
Repository created2022-04-25 20:23:342022-04-25
Data last updated2026-10-26 12:02:2023 days ago
Last commit2025-12-07 09:02:2011 months ago
CommitLatest commit
Committed by xbpeng. Update Category: Documentation Updates. Commit details: Update README.md. This update refines the documentation for easier onboarding.