← Search

Kihyun Yu

2 accepted papers

2025

An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints

ICML 2025poster

Online safe reinforcement learning (RL) plays a key role in dynamic environments, with applications in autonomous driving, robotics, and cybersecurity. The objective is to learn optimal policies that maximize rewards while satisfying safety constraints modeled by constrained Markov decision processe…

Cited by 0SourcePDFScholar