arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0810.3451cs.AIcs.CCcs.LG
收藏

乐观主义的许多面孔-扩展版

The many faces of optimism - Extended version

István Szita, András Lőrincz

摘要:

探索-利用困境一直是强化学习框架内一个有趣且尚未解决的问题。“面对不确定性的乐观”和模型构建在先进的勘探方法中发挥着核心作用。在这里,我们综合几个概念,并获得一个快速和简单的算法。我们表明,该算法发现一个接近最优的政策在多项式时间,并给出实验证据,它是强大的和有效的相比,其优势。

英文摘要:

The exploration-exploitation dilemma has been an intriguing and unsolved problem within the framework of reinforcement learning. "Optimism in the face of uncertainty" and model building play central roles in advanced exploration methods. Here, we integrate several concepts and obtain a fast and simple algorithm. We show that the proposed algorithm finds a near-optimal policy in polynomial time, and give experimental evidence that it is robust and efficient compared to its ascendants.

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。

↑