OmniSafe is an infrastructural framework for accelerating SafeRL research.
NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Be...
NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe ...
Reading list for adversarial perspective and robustness in deep reinforc...
The Verifiably Safe Reinforcement Learning Framework
Safe-RLHF: Constrained Value Alignment via Safe Reinforcement Learning f...
Training (hopefully) safe agents in gridworlds