arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1202.3750cs.LGstat.ML
收藏

Bandit问题的分数阶矩

Fractional Moments on Bandit Problems

Indian Institute of Technology Madras(印度马德拉斯理工学院)

Ananda Narayanan B, Balaraman Ravindran

摘要:

强化学习解决了探索发现有利可图的行为和利用根据已经做出的最佳观察采取行动之间的困境。Bandit问题是无状态环境中的一类问题,代表了这种探索/利用情况。提出了一种基于分数期望的强盗问题的学习算法。理论上证明了该算法收敛于η-最优臂,并实现了O(n)的样本复杂度。实验结果表明,该算法产生的遗憾大大低于参数优化的eta-greedy和SoftMax方法和其他低样本复杂度的最先进的技术。

英文摘要:

Reinforcement learning addresses the dilemma between exploration to find profitable actions and exploitation to act according to the best observations already made. Bandit problems are one such class of problems in stateless environments that represent this explore/exploit situation. We propose a learning algorithm for bandit problems based on fractional expectation of rewards acquired. The algorithm is theoretically shown to converge on an eta-optimal arm and achieve O(n) sample complexity. Experimental results show the algorithm incurs substantially lower regrets than parameter-optimized eta-greedy and SoftMax approaches and other low sample complexity state-of-the-art techniques.

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。

↑