Testing Optimality of Sequential Decision-Making
This paper provides a statistical method to test whether a system that performs a binary sequential hypothesis test is optimal in the sense of minimizing the average decision times while taking decisions with given reliabilities. The proposed method requires samples of the decision times, the decision outcomes, and the true hypotheses, but does not require knowledge on the statistics of the observations or the properties of the decision-making system. The method is based on fluctuation relations for decision time distributions which are proved for sequential probability ratio tests. These relations follow from the martingale property of probability ratios and hold under fairly general conditions. We illustrate these tests with numerical experiments and discuss potential applications.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingSequential Decision MakingSimilar Papers 제목 키워드 기반
Large Language Models for Sequential Decision-Making: Improving In-Context Learning via Supervised Fine-Tuning
Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities, yet their potential for sequential decision-making remains underexplored. In this paper, we study the ICL capabilities of LLMs in…
On Optimal Decision-Making in Ant Colonies
Colonies of ants can collectively choose the best of several nests, even when many of the active ants who organize the move visit only one site. Understanding such a behavior can help us design efficient distributed deci…
Decision MakingStructure-Adaptive Sequential Testing for Online False Discovery Rate Control
Consider the online testing of a stream of hypotheses where a real--time decision must be made before the next data point arrives. The error rate is required to be controlled at {all} decision points. Conventional \emph{…
Decision MakingSequential Decision MakingvalidUNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models
Sequential decision-making refers to algorithms that take into account the dynamics of the environment, where early decisions affect subsequent decisions. With large language models (LLMs) demonstrating powerful capabili…
Decision MakingSequential Decision MakingTowards Improving Sequential Decision-Making in LLM Agents via Experience Memory
Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well understood. We study this on fully-observable two-player zero-sum games, …