by Yohei Hosoe Papers
2 papers found
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
Toshinori Kitamura, Tadashi Kozuno, Wataru Kumagai et al.
ICLR 2025poster
Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno et al.
NeurIPS 2025spotlightarXiv:2502.10138