3 papers
cs.AI2026
Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts
Toshihide Ubukata, Zhiyao Wang, Enhong Mu +2
On-the-fly Directed Controller Synthesis (OTF-DCS) mitigates state-space explosion by incrementally exploring the system and relies critically on an exploration policy to guide sea…
cs.AI2025
Graph Contextual Reinforcement Learning for Efficient Directed Controller Synthesis
Toshihide Ubukata, Enhong Mu, Takuto Yamauchi +3
Controller synthesis is a formal method approach for automatically generating Labeled Transition System (LTS) controllers that satisfy specified properties. The efficiency of the s…
cs.LG2024
Diffusion Model for Planning: A Systematic Literature Review
Toshihide Ubukata, Jialong Li, Kenji Tei
Diffusion models, which leverage stochastic processes to capture complex data distributions effectively, have shown their performance as generative models, achieving notable succes…