Goto

Collaborating Authors

 Reinforcement Learning






TowardsTrustworthyAutomaticDiagnosisSystemsby EmulatingDoctors'ReasoningwithDeep ReinforcementLearning

Neural Information Processing Systems

Moreover,doctors explicitly explore severepathologies before potentially ruling them out from the differential, especially in acute care settings. Finally, for doctors to trust a system's recommendations, they need to understand how the gathered evidences led to the predicted diseases.




Adversarially Robust Decision Transformer

Neural Information Processing Systems

However, in adversarial environments, these methods can be non-robust, since the return is dependent on the strategies of both the decision-maker and adversary. Training a probabilistic model conditioned on observed return to predict action can fail to generalize, as the trajectories that achieve a return in the dataset might have done so due to a suboptimal behavior adversary.