5 papers
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…
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…
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…
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…
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…