Cooperative Coevolution of Neural Networks in Sequential Decision Tasks
顺序决策任务中神经网络的协同协同进化
基本信息
- 批准号:0083776
- 负责人:
- 金额:$ 41.91万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2000
- 资助国家:美国
- 起止时间:2000-09-15 至 2004-08-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
In sequential decision tasks such as resource optimization, robot control, and game playing, several decisions must be made before the outcome can be evaluated. Such reinforcement feedback depends on the entire sequence of decisions, and it is difficult to determine which of the decisions were responsible for the outcome. This project aims at developing better techniques for learning in domains with such sparse feedback, based on evolving neural networks with genetic algorithms. The goal is both to be able to solve existing problems faster, and to be able to solve problems that have not been feasible as sequential decision tasks before. Our previous work showed that neuroevolution is most powerful when individual neurons are evolved to cooperate and form good networks. In this project, such cooperative coevolution methods are studied in depth. The research aims at answering three main questions: Where does the power of cooperative coevolution come from and what are the best ways of making use of it? How do the evolutionary reinforcement learning methods differ from the traditional value function methods in learning sequential decision tasks? Does evolutionary reinforcement learning have the accuracy and flexibility required in real-world applications? If successful, the project will result in cooperative coevolution algorithms that will solve existing sequential decision tasks faster, and will allow solving more difficult tasks than before. We will know how to decide between evolutionary and value function methods for a given reinforcement learning task, and also how to use each method most effectively. Finally, the project will demonstrate how learning in general, and cooperative coevolution of neural networks in particular, can be used to save resources and achieve complex behavior in challenging real-world tasks.
在诸如资源优化、机器人控制和游戏等顺序决策任务中,在评估结果之前必须做出多个决策。这种强化反馈依赖于整个决策序列,很难确定哪些决策对结果负责。 该项目旨在开发更好的技术,在这样的稀疏反馈域学习,基于进化神经网络与遗传算法。目标是能够更快地解决现有问题,并能够解决以前作为顺序决策任务不可行的问题。 我们之前的工作表明,当单个神经元进化到合作并形成良好的网络时,神经进化是最强大的。 本项目对这种协同进化方法进行了深入的研究。这项研究旨在回答三个主要问题: 合作共同进化的力量从何而来?利用它的最佳方式是什么? 进化强化学习方法在学习序列决策任务时与传统的值函数方法有何不同? 进化强化学习是否具有现实世界应用所需的准确性和灵活性? 如果成功,该项目将产生合作的共同进化算法,将更快地解决现有的顺序决策任务,并将允许解决比以前更困难的任务。 我们将知道如何在给定的强化学习任务中选择进化方法和值函数方法,以及如何最有效地使用每种方法。 最后,该项目将展示如何学习,特别是神经网络的合作共同进化,可以用来节省资源,并在具有挑战性的现实世界任务中实现复杂的行为。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Risto Miikkulainen其他文献
Holdout Evaluation
坚持评估
- DOI:
10.1007/978-0-387-30164-8_369 - 发表时间:
2010 - 期刊:
- 影响因子:0
- 作者:
Antal van den Bosch;B. Hengst;J. Lloyd;Risto Miikkulainen;Hendrik Blockeel - 通讯作者:
Hendrik Blockeel
MARLEDA: Effective distribution estimation through Markov random fields
- DOI:
10.1016/j.tcs.2015.07.049 - 发表时间:
2016-06-20 - 期刊:
- 影响因子:
- 作者:
Matthew Alden;Risto Miikkulainen - 通讯作者:
Risto Miikkulainen
Evolutionary Supervised Machine Learning
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:0
- 作者:
Risto Miikkulainen - 通讯作者:
Risto Miikkulainen
Extracting the dynamics of the Hodgkin-Huxley model using recurrent neural networks
- DOI:
10.1186/1471-2202-8-s2-p100 - 发表时间:
2007-07-06 - 期刊:
- 影响因子:2.300
- 作者:
Sari Andoni;Manish Saggar;Tekin Meriçli;Risto Miikkulainen - 通讯作者:
Risto Miikkulainen
Designing neural networks through neuroevolution
通过神经进化设计神经网络
- DOI:
10.1038/s42256-018-0006-z - 发表时间:
2019-01-07 - 期刊:
- 影响因子:23.900
- 作者:
Kenneth O. Stanley;Jeff Clune;Joel Lehman;Risto Miikkulainen - 通讯作者:
Risto Miikkulainen
Risto Miikkulainen的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Risto Miikkulainen', 18)}}的其他基金
Collaborative Research: MOD and TLS: A Predictive Simulation Model of Competitive Dynamics in Innovation
合作研究:MOD 和 TLS:创新竞争动态的预测模拟模型
- 批准号:
0914796 - 财政年份:2009
- 资助金额:
$ 41.91万 - 项目类别:
Standard Grant
RI: Small: Learning Strategic Behavior in Sequential Decision Tasks
RI:小:学习顺序决策任务中的策略行为
- 批准号:
0915038 - 财政年份:2009
- 资助金额:
$ 41.91万 - 项目类别:
Standard Grant
Pilot: Leveraging Human Creativity with Machine Discovery
试点:通过机器发现利用人类创造力
- 批准号:
0757479 - 财政年份:2008
- 资助金额:
$ 41.91万 - 项目类别:
Standard Grant
RI: Mastodon: A Large-Memory, High-Throughput Simulation Infrastructure
RI:Mastodon:大内存、高吞吐量的模拟基础设施
- 批准号:
0303609 - 财政年份:2003
- 资助金额:
$ 41.91万 - 项目类别:
Continuing Grant
Modeling Development and Perceptual Phenomena in the Visual Cortex
视觉皮层的建模发展和感知现象
- 批准号:
9811478 - 财政年份:1998
- 资助金额:
$ 41.91万 - 项目类别:
Standard Grant
Symbiotic Evolution of Neural Networks in Sequential Decision Tasks
神经网络在顺序决策任务中的共生进化
- 批准号:
9504317 - 财政年份:1995
- 资助金额:
$ 41.91万 - 项目类别:
Continuing Grant
RIA: A Self-Organizing Neural Network Model of The PrimaryVisual cortex
RIA:初级视觉皮层的自组织神经网络模型
- 批准号:
9309273 - 财政年份:1993
- 资助金额:
$ 41.91万 - 项目类别:
Standard Grant
相似海外基金
NSF Postdoctoral Fellowship in Biology: Human Domestication of Maize as Bio-cultural Coevolution
美国国家科学基金会生物学博士后奖学金:人类驯化玉米作为生物文化协同进化
- 批准号:
2305694 - 财政年份:2024
- 资助金额:
$ 41.91万 - 项目类别:
Fellowship Award
CAREER: Understanding biosphere-geosphere coevolution through carbonate-associated phosphate, community archives, and open-access education in rural schools
职业:通过碳酸盐相关磷酸盐、社区档案和农村学校的开放教育了解生物圈-地圈协同进化
- 批准号:
2338055 - 财政年份:2024
- 资助金额:
$ 41.91万 - 项目类别:
Continuing Grant
Postdoctoral Research Fellowship in Biology: The Coevolution of Climate Change Responses in Grasses
生物学博士后研究金:草类气候变化响应的共同进化
- 批准号:
2209408 - 财政年份:2023
- 资助金额:
$ 41.91万 - 项目类别:
Fellowship Award
Investigation of responsible genetic basis for male and female coevolution of exaggerated genitalia
夸张生殖器男女共同进化的遗传基础研究
- 批准号:
22KJ3101 - 财政年份:2023
- 资助金额:
$ 41.91万 - 项目类别:
Grant-in-Aid for JSPS Fellows
Inferring the gene coevolution network from deep comparative genomics
从深度比较基因组学推断基因协同进化网络
- 批准号:
2241312 - 财政年份:2023
- 资助金额:
$ 41.91万 - 项目类别:
Standard Grant
Genetic basis of rapid coevolution of morphological traits between sexes
两性形态性状快速协同进化的遗传基础
- 批准号:
23H02530 - 财政年份:2023
- 资助金额:
$ 41.91万 - 项目类别:
Grant-in-Aid for Scientific Research (B)
Development of high-resolution X-ray telescope for studying the coevolution of galaxies and black holes
开发用于研究星系和黑洞共同演化的高分辨率X射线望远镜
- 批准号:
23H00128 - 财政年份:2023
- 资助金额:
$ 41.91万 - 项目类别:
Grant-in-Aid for Scientific Research (A)
Discover and verify principles of coevolution using laboratory evolution accelerated by transposons
利用转座子加速的实验室进化发现并验证共同进化的原理
- 批准号:
22KJ0578 - 财政年份:2023
- 资助金额:
$ 41.91万 - 项目类别:
Grant-in-Aid for JSPS Fellows
Revealing coevolution of supermassive black holes and host galaxies with the gravitational wave background
引力波背景揭示超大质量黑洞与宿主星系的协同演化
- 批准号:
23K03460 - 财政年份:2023
- 资助金额:
$ 41.91万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Causes and consequences of intra-genomic coevolution
基因组内协同进化的原因和后果
- 批准号:
10644124 - 财政年份:2023
- 资助金额:
$ 41.91万 - 项目类别: