arXivDaily arXiv每日学术速递 周一至周五更新
arXiv cs/0502067cs.LGcs.AI
收藏

基于损失值递增的主动专家问题的主算法

Master Algorithms for Active Experts Problems based on Increasing Loss Values

Jan Poland, Marcus Hutter

摘要:

我们指定一个专家算法具有以下特点:(a)它只使用实际选择的行动(强盗设置)的反馈,(b)它可以应用于可数无限的专家类,(c)它处理的损失,可能会在适当的时间缓慢增长。我们证明了一个自适应对手的损失范围。由此,我们获得了“主动专家问题”的主算法,这意味着主的行为可能会影响对手的行为。我们的算法可以显着优于标准的专家算法在这样的问题。最后,我们将其与通用专家类相结合。这导致了一个(计算上不可行的)通用主算法,它在某种意义上几乎和任何在线问题的任何可计算策略一样好。

英文摘要:

We specify an experts algorithm with the following characteristics: (a) it uses only feedback from the actions actually chosen (bandit setup), (b) it can be applied with countably infinite expert classes, and (c) it copes with losses that may grow in time appropriately slowly. We prove loss bounds against an adaptive adversary. From this, we obtain master algorithms for "active experts problems", which means that the master's actions may influence the behavior of the adversary. Our algorithm can significantly outperform standard experts algorithms on such problems. Finally, we combine it with a universal expert class. This results in a (computationally infeasible) universal master algorithm which performs - in a certain sense - almost as well as any computable strategy, for any online problem.

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。

↑