RI: Small: General Intelligence through Algorithm Invention and Selection

RI：小：通过算法发明和选择实现通用智能

• 批准号: 1717324
• 负责人: Julian Togelius
• 金额: $ 42.7万
• 依托单位: New York University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-01 至 2020-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1717324&HistoricalAwards=false
• 关键词: RI; Small; General; Intelligence; through

Creating better artificial intelligence has plenty of applications in different areas of society, from self-driving cars and aircraft to production planning, control of machines and music composition. Most current artificial intelligence research focuses on creating algorithms that can only do a single thing, or solve a single problem. To achieve artificial general intelligence we must learn how to create algorithms that can solve many different problems, without a human having to adjust the algorithm for every problem. The research in this project aims to understand how such artificial general intelligence can be created. The basic idea is to build algorithms that can create their own more specific algorithms, and learn to automatically select the right algorithm for the right problem. In order to develop these algorithms, we need a large set of good problems to test them on. Games are widely used to test AI algorithms, because they model real-world problems but are fast and easy to execute. The general algorithms developed in this project will be tested on a set of classic games, and a real-time strategy game.This research project aims to investigate how we can create more general artificial intelligence through online stochastic search for algorithms, combined with and informed by online selection among discovered algorithms. In other words, the project will investigate the combination of genetic programming in the space of tree search algorithms with algorithm selection, also called hyper-heuristics, for creating more general problem-solving abilities. These capabilities will be evaluated through a sequence of experiments on two different test beds. Successful completion of the research will clarify the potential of search in algorithm space as a method for creating more general artificial intelligence, and produce a number of algorithms. This includes both the algorithms that will be designed for searching for algorithms and searching among algorithms, as well as the new algorithms that will be discovered by the search in algorithm space. The methods produced are expected to ultimately be generally applicable to a large number of problems.

创造更好的人工智能在社会的不同领域都有大量应用，从自动驾驶汽车和飞机到生产规划、机器控制和音乐创作。当前大多数人工智能研究都集中在创建只能做单一事情或解决单一问题的算法。 为了实现通用人工智能，我们必须学习如何创建能够解决许多不同问题的算法，而无需人类为每个问题调整算法。该项目的研究旨在了解如何创建这种通用人工智能。基本思想是构建可以创建自己的更具体算法的算法，并学习为正确的问题自动选择正确的算法。为了开发这些算法，我们需要大量好的问题来测试它们。游戏被广泛用于测试人工智能算法，因为它们模拟现实世界的问题，但速度快且易于执行。本项目开发的通用算法将在一组经典游戏和一款即时战略游戏上进行测试。本研究项目旨在研究如何通过在线随机搜索算法，结合并告知信息来创建更通用的人工智能。通过在线选择发现的算法。换句话说，该项目将研究树搜索算法空间中的遗传编程与算法选择（也称为超启发式）的结合，以创造更通用的解决问题的能力。这些功能将通过两个不同测试台上的一系列实验进行评估。 该研究的成功完成将阐明算法空间中的搜索作为创建更通用人工智能的方法的潜力，并产生许多算法。这既包括为算法搜索和算法间搜索而设计的算法，也包括通过在算法空间中搜索发现的新算法。所产生的方法预计最终将普遍适用于大量问题。

项目成果

ELIMINATION from Design to Analysis

从设计到分析的消除

• DOI: 10.1109/cig.2019.8848017
• 发表时间: 2019
• 期刊: 2019 IEEE Conference on Games (CoG
• 作者: Khalifa, Ahmed;Gopstein, Dan;Togelius, Julian
• 通讯作者: Togelius, Julian

Talakat: bullet hell generation through constrained map-elites

Talakat：通过受限的地图精英生成弹幕地狱

• 发表时间: 2018
• 期刊: 2018 Genetic and Evolutionary Computation Conference (GECCO
• 作者: Khalifa, Ahmed;Lee, Scott;Nealen, Andy;Togelius, Julian
• 通讯作者: Togelius, Julian

Level Design Patterns in 2D Games

• DOI: 10.1109/cig.2019.8847953
• 发表时间: 2019-08
• 期刊: 2019 IEEE Conference on Games (CoG)
• 作者: A. Khalifa;F. Silva;J. Togelius

Intentional computational level design

• DOI: 10.1145/3321707.3321849
• 发表时间: 2019-04
• 期刊: Proceedings of the Genetic and Evolutionary Computation Conference
• 作者: A. Khalifa;M. Green;Gabriella A. B. Barros;J. Togelius

Deep learning for procedural content generation

• DOI: 10.1007/s00521-020-05383-8
• 发表时间: 2020-10-08
• 期刊: NEURAL COMPUTING & APPLICATIONS
• 影响因子: 6
• 作者: Liu, Jialin;Snodgrass, Sam;Togelius, Julian
• 通讯作者: Togelius, Julian