arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.00357cs.GT
收藏

竞争主体的先知不等式

Prophet Inequality with Competing Agents

Tomer Ezra, Michal Feldman, Ron Kupfer

摘要:

我们引入了一个模型的竞争代理人在先知设置,奖励到达网上,并立即作出决定,可追溯性。奖励从一开始就是未知的,但它们是从已知的概率分布中得出的。在标准的预言者设定中,单个智能体做出选择决策,试图最大化她的预期回报。我们的模型的新颖之处在于引入了竞争环境,在这种环境中,多个代理竞争即将到来的奖励,并在奖励到达时同时做出在线选择决策。如果一个给定的奖励是由一个以上的代理人选择的,那么关系就会被随机打破,或者被代理人的固定排名打破。竞争的考虑将先知设置从在线决策场景转变为多代理游戏。对于随机和排名抢七规则,我们提出了简单的阈值策略的代理,给他们很高的保证,独立于其他人所采取的策略。特别地,对于随机平局决胜,每个智能体可以保证自己至少获得最高奖励的$\frac{1}{k+1}$和最优社会福利的至少$\frac{1}{2k}$。对于排名抢七,排名$i$的代理可以保证自己至少获得第$i$最高奖励的一半。我们补充这些结果匹配的上限,甚至相对于平衡配置文件。对于排名平局打破规则,我们还显示了平衡的$k$代理游戏和一个单一的决策者谁可以选择最多$k$奖励的最优策略之间的对应关系。

英文摘要:

We introduce a model of competing agents in a prophet setting, where rewards arrive online, and decisions are made immediately and irrevocably. The rewards are unknown from the outset, but they are drawn from a known probability distribution. In the standard prophet setting, a single agent makes selection decisions in an attempt to maximize her expected reward. The novelty of our model is the introduction of a competition setting, where multiple agents compete over the arriving rewards, and make online selection decisions simultaneously, as rewards arrive. If a given reward is selected by more than a single agent, ties are broken either randomly or by a fixed ranking of the agents. The consideration of competition turns the prophet setting from an online decision making scenario to a multi-agent game. For both random and ranked tie-breaking rules, we present simple threshold strategies for the agents that give them high guarantees, independent of the strategies taken by others. In particular, for random tie-breaking, every agent can guarantee herself at least $\frac{1}{k+1}$ of the highest reward, and at least $\frac{1}{2k}$ of the optimal social welfare. For ranked tie-breaking, the $i$th ranked agent can guarantee herself at least a half of the $i$th highest reward. We complement these results by matching upper bounds, even with respect to equilibrium profiles. For ranked tie-breaking rule, we also show a correspondence between the equilibrium of the $k$-agent game and the optimal strategy of a single decision maker who can select up to $k$ rewards.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑