ProjectFeatured
Safety-Gymnasium
Safe RL environments maintained under Farama — successor path for Safety-Gym style tasks.
ProjectFeaturedIntermediate
OmniSafe
Comprehensive library for safe reinforcement learning algorithms and benchmarks.
Why: Broad open Safe-RL algorithm zoo
Overview
OmniSafe is a curated project on Embodied AI Hub.
Comprehensive library for safe reinforcement learning algorithms and benchmarks.
Why it matters: Broad open Safe-RL algorithm zoo
Always verify install pins, licenses, and hardware requirements on the official site before production use.
Who it is for
Builders mapping open embodied stacks; researchers comparing SOTA baselines.
Key highlights
- Comprehensive library for safe reinforcement learning algorithms and benchmarks.
- Type: project; tags: 安全, 强化学习, 开源, 中国
- Hub recommended
When to use
- You need this category of open resource in your stack map
- You are shortlisting baselines before deep evaluation
When not to use
- License or hardware constraints block adoption
- You only need a closed commercial stack with vendor SLA
Getting started
- 1Open the official URL and read the README / model card.
- 2Check license and citation requirements.
- 3Run the smallest official example before scaling.
- 4Cross-link related hub resources for a full pipeline.
Install / setup
pip
pip install omnisafe
How it compares
Broad Safe-RL zoo; for control-theoretic safety also see CBFs / safe-control-gym.
Caveats & pitfalls
- Hub cards are curated summaries — verify upstream docs.
- Stars and release names drift; treat metadata as approximate.
Content reviewed 2026-07-28