Intelligent Systems in Nanjing University
Intelligent Systems in Nanjing University
复制标题
南京大学智能系统
DOI：
--
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
商琳
中科院分区：
文献类型：
--
作者：
商琳
智能系统是南京大学的一个重大研究主题，得到了中国新型软件技术国家重点实验室的支持，该实验室是全国信息技术领域的顶级实验室之一。目前，南京大学智能系统小组开展的研究主要集中在以下几个方面：•智能计算的基本方法，特别是强化学习、增量学习、颗粒计算和粗糙集。•智能代理和多代理系统。•基于内容的多媒体（图像和3D模型）检索。智能系统组旨在设计智能算法和系统来有效地处理实际问题。该团队开发的软件工具和应用程序涵盖了广泛的领域，包括医疗、公共安全和虚拟游戏。强化学习是一种在线的增量学习技术，通过这种技术，智能代理通过试错与周围世界进行交互，并根据强化信号学习决策序列的最佳策略。我们的团队研究了各种强化学习问题的算法，包括平均奖励强化学习、多智能体强化学习、关系强化学习、强化学习中的函数逼近和选项发现等。例如，我们的g学习算法解决了平均奖励域，并且比经典的r学习和q学习更稳定。下图显示了访问控制排队任务中每10000步计算的平均奖励的四条曲线。如图所示，g学习优于r学习及其在学习速度上的变化。除了理论算法研究外，该小组还研究了强化学习的应用。所提出的算法已被应用于视频游戏任务，如俄罗斯方块。该小组参加了RL 2008比赛，并在俄罗斯方块游戏中获得了第六名。学习分类器系统的研究也与强化学习有关。我们的团队已经成功地将学习分类器系统技术应用于不同的问题领域，包括数据挖掘、医疗数据分析和图像隐写检测。•粗糙集粗糙集理论是处理不精确、不确定和模糊信息的可靠数学工具。该小组在这一领域的大部分工作可以用基于粗糙集的分类和特征选择的混合方法来表征。针对不完全信息系统，提出了GDT（General Distribution Table）规则生成方法和默认规则提取方法。增量算法很重要，因为数据源的数量越来越多。该小组调查了……
Intelligent systems is a major research theme in Nanjing University, with the support from the State Key Laboratory for Novel Software Technology of China, one of the top laboratories in the information technology field in the whole country. Currently, the research carried out by the intelligent systems group at Nanjing University mainly fo-cuses on the following topics: • Fundamental methods of intelligent computing, particularly reinforcement learning, incremental learning , granular computing and rough sets. • Intelligent agents and multi-agent systems. • Content-based multimedia (images and 3D models) retrieval. The intelligent systems group aims to design intelligent algorithms and systems to deal with real problems efficiently. The group has developed software tools and applications covering wide areas, including medical treatment, public security, and virtual games. • Reinforcement learning Reinforcement learning is an on-line, incremental learning technology, by which intelligent agents interact with the surrounding world by trial-and-error, and learn the optimal policy of decision sequences according to reinforcement signals. Our group has studied various algorithms for reinforcement learning problems, including average reward reinforcement learning, multi-agent reinforcement learning, relational reinforcement learning, function approximation in reinforcement learning and option discovery , etc. For example, our G-learning algorithm addresses the average reward domain, and is more stable than the classical R-learning and Q-learning. The following figure shows four curves of the average rewards computed in every 10,000 steps in the access-control queuing task. As shown in this figure, G-learning outperforms R-learning and its variation in the learning speed. Besides the theoretical algorithm research , the group also studies the application of reinforcement learning. The proposed algorithms have been applied to video game tasks such as Tetris. The group attended the RL 2008 competition and won the 6th place in the game of Tetris. Research in learning classi-fier systems is related to reinforcement learning as well. Our group has successfully applied the learning classifier systems technology to different problem domains including data mining, medical data analysis and image steganography detection. • Rough set Rough set theory is a sound mathematical tool to deal with imprecise, uncertain, and vague information. Most of the group's work in this area can be characterized by rough-set-based hybrid approaches in classification and features selection. For incomplete information systems, rule generation by the GDT(General Distribution Table) approach and a default rule extracting method were proposed. Incremental algorithms are important, as data sources are increasingly in quantity. The group has investigated the …