LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy

Open Webpage

Hsin-Jung Yang, Zhanhong Jiang, Prajwal Koirala, Qisai Liu, Cody H. Fleming, Soumik Sarkar

Published: 2026, Last Modified: 13 May 2026CoRR 2026EveryoneRevisionsBibTeXCC BY-SA 4.0