skrl

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.

skrl is currently grouped under RAG / Knowledge Base, which makes it easier to evaluate through workflow fit instead of isolated features alone. Based on the available data, it leans most heavily toward Modular and extensible design and Developing and testing new Reinforcement Learning algorithms. It also shows measurable community traction with 1.1k GitHub stars.