.png){kind=icon}
.png){kind=icon}
Return
Intermittently Observable Markov Decision Processes
.png){kind=icon}
PRE
AI
DOI：10.1109/TAC.2025.3603304.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article investigates Markov decision processes (MDPs) with intermittent state information. We consider a scenario where the controller perceives the state of the process via an unreliable communication channel. The transmissions of state information over the whole time horizon are modeled as a Bernoulli lossy process. Hence, the problem is finding an optimal policy for selecting actions in the presence of state information losses. We first formulate the problem as a belief MDP to establish structural results. The effect of state information losses on the expected total discounted reward is studied systematically. Then, we reformulate the problem as a tree MDP whose state space is organized in a tree structure. Two finite-state approximations to the tree MDP are developed to find near-optimal policies efficiently. Finally, we put forth a nested value iteration algorithm for the two approximations, which is proved to be faster than standard value iteration. Numerical results demonstrate the effectiveness of our methods.
Keywords:
Markov decision process (MDP)
nested value iteration (NVI)
state information losses
structural results
truncated approximation
Journal
IF:
7
Papers:
1.3W
Citations:
6.7W