代码库
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Python
ai-safetyalpacabeaverdatasetsdeepspeedgptlarge-language-modelsllamallmllmsreinforcement-learningreinforcement-learning-from-human-feedbackrlhfsafe-reinforcement-learningsafe-reinforcement-learning-from-human-feedbacksafe-rlhfsafetytransformertransformersvicuna
JMLR: OmniSafe is an infrastructural framework for accelerating SafeRL research.
Python
benchmarkconstraint-rlconstraint-satisfaction-problemdeep-learningdeep-reinforcement-learningmachine-learningpytorchreinforcement-learningsafe-reinforcement-learningsafe-rlsaferlsafety-criticalsafety-gymsafety-gymnasium