arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.07570cs.GTcs.DScs.LG
收藏

贝叶斯探索:贝叶斯博弈中的激励探索

Bayesian Exploration: Incentivizing Exploration in Bayesian Games

Microsoft Research(微软研究院);Tel Aviv University(特拉维夫大学);University of Pennsylvania(宾夕法尼亚大学);Carnegie Mellon University(卡内基梅隆大学)

Yishay Mansour, Aleksandrs Slivkins, Vasilis Syrgkanis, Zhiwei Steven Wu

摘要:

我们认为在互联网经济中无处不在的情况下,个人决策者(以下简称为代理人)都生产和消费信息,因为他们在一个不确定的环境中做出战略选择。这在探索(尝试未充分探索的替代方案,以在未来帮助他人)、利用(根据其他代理人发现的信息做出最佳决策)和代理人的激励(他们对利用感兴趣,同时更喜欢其他人探索)之间产生了三方权衡。我们的委托人控制来自之前代理的信息流,并努力协调代理在探索和开发之间实现社会最佳平衡,而不使用任何货币转移。我们的目标是为委托人设计一个推荐策略,既尊重代理人的激励,又尽量减少合适的后悔概念。我们在这个方向上扩展了以前的工作,允许代理在一个共享的环境中彼此交互:在每个时间步,多个代理到达玩贝叶斯游戏,接收建议,选择他们的行动,接收他们的收益,然后永远离开游戏。代理人现在面临两个来源的不确定性:其他代理人的行动和不确定的游戏环境的参数。我们的主要贡献是表明,校长可以实现常数后悔时,效用是确定性的(其中常数取决于先验分布,但不是时间范围),对数后悔时,效用是随机的。作为一个关键的技术工具,我们引入了可探索行动的概念,一些激励相容的政策可以推荐非零概率的行动。我们展示了如何主要可以识别(和探索)所有可探索的行动,并使用所揭示的信息来执行最佳。

英文摘要:

We consider a ubiquitous scenario in the Internet economy when individual decision-makers (henceforth, agents) both produce and consume information as they make strategic choices in an uncertain environment. This creates a three-way tradeoff between exploration (trying out insufficiently explored alternatives to help others in the future), exploitation (making optimal decisions given the information discovered by other agents), and incentives of the agents (who are myopically interested in exploitation, while preferring the others to explore). We posit a principal who controls the flow of information from agents that came before, and strives to coordinate the agents towards a socially optimal balance between exploration and exploitation, not using any monetary transfers. The goal is to design a recommendation policy for the principal which respects agents' incentives and minimizes a suitable notion of regret. We extend prior work in this direction to allow the agents to interact with one another in a shared environment: at each time step, multiple agents arrive to play a Bayesian game, receive recommendations, choose their actions, receive their payoffs, and then leave the game forever. The agents now face two sources of uncertainty: the actions of the other agents and the parameters of the uncertain game environment. Our main contribution is to show that the principal can achieve constant regret when the utilities are deterministic (where the constant depends on the prior distribution, but not on the time horizon), and logarithmic regret when the utilities are stochastic. As a key technical tool, we introduce the concept of explorable actions, the actions which some incentive-compatible policy can recommend with non-zero probability. We show how the principal can identify (and explore) all explorable actions, and use the revealed information to perform optimally.

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。

↑