arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.03456cs.LGcs.AIstat.ML
收藏

永别了,武器:有放弃选项的预算序列奖励最大化

A Farewell to Arms: Sequential Reward Maximization on a Budget with a Giving Up Option

University of Victoria(维多利亚大学);Google(谷歌)

P Sharoff, Nishant A. Mehta, Ravi Ganti

摘要:

我们考虑一个顺序决策问题,其中一个代理可以在一个时间采取一个行动,每个行动有一个随机的时间范围,即,在前一个动作完成之前不能采取新的动作。完成后,所选择的动作产生随机奖励。代理人寻求在有限的时间预算内最大化其累积奖励,并可以选择“放弃”当前的行动-因此放弃任何奖励-以便选择另一个行动。我们把这个问题作为一个变种的随机多武装土匪问题的随机消耗资源。对于这个问题,我们首先建立了最优的手臂是一个最大化的比率的预期回报的手臂的预期等待时间之前,代理人看到的回报,由于拉手臂。使用一个新的置信度上界这个比率,然后我们引入了一个上置信度为基础的算法,WAIT-UCB,我们建立对数,问题相关的遗憾界,其中有一个改进的依赖问题的参数相比,以前的作品。各种问题的配置比较WAIT-UCB对国家的最先进的算法的模拟。

英文摘要:

We consider a sequential decision-making problem where an agent can take one action at a time and each action has a stochastic temporal extent, i.e., a new action cannot be taken until the previous one is finished. Upon completion, the chosen action yields a stochastic reward. The agent seeks to maximize its cumulative reward over a finite time budget, with the option of "giving up" on a current action -- hence forfeiting any reward -- in order to choose another action. We cast this problem as a variant of the stochastic multi-armed bandits problem with stochastic consumption of resource. For this problem, we first establish that the optimal arm is the one that maximizes the ratio of the expected reward of the arm to the expected waiting time before the agent sees the reward due to pulling that arm. Using a novel upper confidence bound on this ratio, we then introduce an upper confidence based-algorithm, WAIT-UCB, for which we establish logarithmic, problem-dependent regret bound which has an improved dependence on problem parameters compared to previous works. Simulations on various problem configurations comparing WAIT-UCB against the state-of-the-art algorithms are also presented.

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。

↑