Verifiably safe exploration for end-to-end reinforcement learningNathan HuntNathan Fultonet al.2021HSCC 2021
Work-in-progress: Verifiably safe scuba diving using commodity sensorsViren BajajKarim Elmaaroufiet al.2019EMSOFT 2019
CertRL: Formalizing convergence proofs for value and policy iteration in CoqKoundinya VajjhaAvraham Shinnaret al.2021CPP 2021