https://openreview.net/forum?id=2FGpL5Nd4C&referrer=%5Bthe%20profile%20of%20Yihao%20Sun%5D(%2Fprofile%3Fid%3D~Yihao_Sun1)
Improving Reward Model Generalization from Adversarial Process Enhanced Preferences | OpenReview
In sequential decision-making, the reward function serves as the primary supervision signal, guiding agents to acquire the desired behaviors. Traditional...
adversarial processimprovingrewardmodelgeneralization