collaborators

5 papers

cs.LG2026

Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying

Soichiro Nishimori, Paavo Parmas, Sotetsu Koyamada +4

In reinforcement learning (RL), agents benefit from exploration only because they repeatedly encounter similar states: trying different actions can improve performance or reduce un…

cs.LG2026

Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form

Toshinori Kitamura, Tadashi Kozuno, Wataru Kumagai +6

Designing a safe policy for uncertain environments is crucial in real-world control systems. However, this challenge remains inadequately addressed within the Markov decision proce…

cs.LG2026

CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation

Yushi Feng, Junye Du, Qifan Wang +5

Graphical user interface (GUI) agents powered by vision language models (VLMs) are rapidly moving from passive assistance to autonomous operation. However, this unrestricted action…

cs.LG2026

Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation

Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno +5

We study the reinforcement learning (RL) problem in a constrained Markov decision process (CMDP), where an agent explores the environment to maximize the expected cumulative reward…

cs.LG2024

A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees

Toshinori Kitamura, Tadashi Kozuno, Masahiro Kato +6

We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs). Despite its widespread practical use, the existing theor…