欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
强化学习方法是人工智能领域中比较重要的方法之一，自从其提出以来已经有了很大的发展，并且能用来解决很多的问题。但是在遇到大规模状态空间问题时，使用普通的强化学习方法就会产生“维数灾”现象，所以提出了关系强化学习，把强化学习应用到关系领域可以在一定的程度上解决“维数灾”难题。在此基础上，简单介绍关系强化学习的概念以及相关的算法，以及以后有待解决的问题。
英文摘要：
Reinforcement learning（RL） is one of the important methods in artificial intelligence field. It has been progressed a lot since being proposed and was used to solve many problems. However, when the state space is very large, there will be ＂curse of dimensionality＂ problem occurred in general reinforcement learning methods. As a result, the relational reinforcement learning, which applies RL to relational technique field, is proposed to solve this problem to some extent. Based on this, the concept of relational reinforcement learning, its related algorithms and some difficulties need to be solved are introduced as well.
同期刊论文项目
同项目期刊论文
位置：