Abstract | ||
---|---|---|
In this paper, we consider non-signaling approximation of finite stochastic teams. We first introduce a hierarchy of team decision rules that can be classified in an increasing order as randomized policies, quantum-correlated policies, and non-signaling policies. Then, we establish an approximation of team-optimal policies for sequential teams via extendible non-signaling policies. We prove that the distance between extendible non-signaling policies and decentralized policies is small if the extension is sufficiently large. Using this result, we establish a linear programming (LP) approximation of sequential teams. Finally, we state an open problem regarding computation of optimal value of quantum-correlated policies. |
Year | Venue | DocType |
---|---|---|
2019 | arXiv: Systems and Control | Journal |
Volume | Citations | PageRank |
abs/1905.07162 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Naci Saldi | 1 | 29 | 10.27 |
Can Deha Kariksiz | 2 | 0 | 0.68 |
Maxim Raginsky | 3 | 771 | 60.65 |
Eric Chitambar | 4 | 0 | 0.34 |