基于Q学习的生物序列比对方法

将寻求两条生物序列最优比对的过程视为Agent自主学习寻找最优策略的过程。用状态集合表示序列中的碱基和为了获得最佳排列插入序列的空格，为Agent每一次行动打分作为立即收益，合计每一种策略的所有立即收益作为该策略的预期收益，获得最大预期收益的策略就是最优策略，与之对应的Agent遍历的状态集合就是最佳排列。给出了时间复杂度和空间复杂度的公式证明，通过实验证明该方法有效地降低了时间复杂度和空间复杂度（O（kh））。

SAQL: A New Approach for Sequence Alignment base on Q-learning

Look on finding the optimal compare result as the progress of the Agent finding the optimal strategy. The state set is used as the expression of the acids and the gaps inset into the alignment aimed to get the optimal Sequence Alignment. Give a score for every action of the Agent as the immediately profits, count all the immediately profits of every strategy as the expected profits, The optimal strategy is the strategy which has the largest expected profits, and the optimal sequence alignment is the state set of the optimal strategy. Give the formula approval of the time complexity and the space complexity, also prove the time complexity and the space complexity reduce to(O(kn))by experiment.