Multi-Agent Sequential Hypothesis Testing: A Sequential Game of Synchronizing Coordination
Kwang-Ki K. Kim and Jeff S. Shamma
Abstract
- This paper considers multi-agent sequential hypothesis testing(다중 에이전트 순차 가설 검정)
- and presents a framework for strategic learning in sequential games
- with explicit consideration of both temporal(시간) and spatial(공간) coordination.
- The associated Bayes risk functions explicitly incorporate costs of taking private/public measurements,
- costs of time-difference(시차) and disagreement(의견충돌) in actions of agents
- and costs of false declaration/choices in the sequential hypothesis testing.
- The corresponding sequential decision processes have well-defined value functions with respect to
(a) the belief states for the case of conditional independent private noisy measurements(조건적으로 독립적인 개별 잡음 측정) that are also assumed to be independent identically distributed(독립적으로 동일하게 분포) over time
(b) the information states for the case of correlated private noisy measurements.
- A sequential investment game of strategic coordination(전략적 조정) and delay(지연) is also discussed as an application of the proposed strategic learning rules.