#partial observability

try —

6 papers match

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…

#partial observability#pomdp#minimal sufficient statistic#stable quotient
cs.GT2026

DNQ: Deep Nash Q-Network for Partially Observable n-Player Games

Qintong Xie, Edward Koh, Xavier Cadet +1

The paper introduces DNQ, a deep reinforcement learning framework that trains bidding agents for partially observable n‑player games by alternating between trajectory collection, c…

#multi-agent reinforcement learning#partial observability#n-player games#equilibrium computation
cs.LG2026

NetForge RL: A Multi-Agent Simulation Environment for Cyber Defense with Durative Actions

Igor Jankowski

The paper introduces NetForge RL, a fast multi‑agent reinforcement‑learning environment that simulates cyber‑defense scenarios on procedurally generated enterprise and OT networks,…

#cyber defense#multi-agent systems#simulation environment#network security
cs.RO2026

Deformable State Estimation for Autonomous Surgical Tissue Retraction Under Partial Observability

Everest Yang, Skye Thompson, George D. Konidaris

The paper presents a learned estimator that reconstructs the full shape of a deformable tissue mesh from a small set of noisy surface points, enabling more accurate planning for su…

#deformable object manipulation#state estimation#partial observability#surgical robotics
cs.MA2026

Multi-Agent LLMs Fail to Explore Each Other

Hyeong Kyu Choi, Jiatong Li, Wendi Li +2

The paper shows that large language model agents struggle to explore each other in multi-agent settings, leading to poor coordination, and introduces the MACE framework that uses s…

#multi-agent exploration#large language models#partial observability#peer selection
math.OC2026

LQG solution for POMDP without estimating states: A minimum variance approach

Ranjan Sarkar, Prabhat K. Mishra

The paper proposes a method to design a Linear Quadratic Gaussian controller for discrete-time linear systems with noisy and incomplete measurements that avoids explicit state esti…

#linear quadratic gaussian#partial observability#minimum variance#state estimation avoidance