collaborators

19 papers

cs.LG2026

Vector Symbolic Policy Gradient

Ryozo Masukawa, Sanggeon Yun, SungHeon Jeong +6

We answer this question with Vector-Symbolic Policy Gradient (VSPG), a discrete-action actor that represents each action by a unit-norm hypervector and scores it by similarity to t…

cs.CR2026

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)

Ryozo Masukawa, Ian Bryant, Armita Kazeminajafabadi +6

Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, h…

cs.LG2026

Minimal Markovization via Stable Quotients in Holonomy-Cover Decision Processes

Zuyuan Zhang, Yongshan Chen, Mahdi Imani +1

The paper defines the smallest memory representation needed for a class of partially observable decision processes called holonomy-cover decision processes, builds a stable quotien…

cs.AI2026

The Topology of Ill-Posed Questions: Persistent Homology for Detection and Steering in LLMs

Guangyu Jiang, Sizhe Tang, Mahdi Imani +1

Ill-posed questions, including ambiguous, underspecified, or contradictory queries, may admit no valid answer or multiple plausible answers, posing a challenge for large language m…

cs.LG2026

FedQHD: Closed-Form Function-Space Federated Reinforcement Learning

Yuchen Hou, Yongshan Chen, Zhuowen Zou +4

Federated reinforcement learning enables decentralized agents to collaboratively improve policies or value estimates without exchanging raw trajectories. However, FedAvg-style para…

cs.LG2026

Metric-Gradient Projection for Stable Multi-Agent Policy Learning

Zuyuan Zhang, Sizhe Tang, Mahdi Imani +1

General-sum multi-agent learning is often governed by a stacked update field in which each agent's policy update changes the optimization landscape faced by the others. This coupli…