skrl
Active·★ 1.1k·MIT·Updated 2026-10-27
★ Essential★ Trending
skrl is an open-source, modular Reinforcement Learning library implemented in Python, supporting PyTorch, JAX, and NVIDIA Warp. It focuses on modularity, readability, simplicity, and transparent algorithm implementation, also supporting various environment interfaces like Gym, Gymnasium, and Isaac Lab.
#Reinforcement Learning#Python#PyTorch#JAX#NVIDIA Warp#Coding
01
Features
01Modular and extensible design
02Transparent algorithm implementation
03Multi-framework support (PyTorch, JAX, NVIDIA Warp)
04Compatibility with various environment interfaces (Gym, Gymnasium, PettingZoo, ManiSkill)
05Simultaneous training in NVIDIA Isaac Lab and MuJoCo Playground with scope-based resource sharing
02
Compatibility
PyTorch
Native
Verified via docs
JAX
Native
Verified via docs
NVIDIA Warp
Native
Verified via docs
OpenAI Gym
Supported
Verified via docs
Farama Gymnasium
Supported
Verified via docs
Farama PettingZoo
Supported
Verified via docs
03
Quick start
1
$ pip install skrl
04
Use cases
↳Developing and testing new Reinforcement Learning algorithms
↳Training AI agents in various simulated environments (e.g., robotic control, game AI)
↳Research in Reinforcement Learning leveraging multiple backend frameworks
05
Alternatives
rlcard★ 3.6k
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
ir-sim★ 1.2k
A Python-based lightweight robot simulator designed for navigation, control, and reinforcement learning
verl-agent★ 2.4k
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
Comments
Log in to leave a comment
No comments yet. Be the first!