Permutation based task transfer for genetic programming
基于排列的遗传编程任务转移
基本信息
- 批准号:RGPIN-2015-06117
- 负责人:
- 金额:$ 1.31万
- 依托单位:
- 依托单位国家:加拿大
- 项目类别:Discovery Grants Program - Individual
- 财政年份:2019
- 资助国家:加拿大
- 起止时间:2019-01-01 至 2020-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
The general context for this research proposal is that of genetic programming (GP) as applied to learning decision making policies for agents operating in environments with delayed payoff (or reinforcement learning). The specific focus of the proposal lies in developing a framework for systematically scaling GP to more difficult versions of tasks with delayed payoff than have previously been considered. In particular we are interested in scenarios in which solutions for a simpler initial `source' task are then `transferred' to a more difficult but related (target) task; or a form of transfer learning. The insight of this work is to make use of the capability of GP to identify solutions that make use of subsets of state variables. This then provides the basis for redeploying solutions discovered under the source task such that more difficult tasks can be solved. The potential benefits of adopting such an approach are that: 1) it is not necessary to continuously rediscover policies from scratch; 2) increased success in / or better solutions to the ultimate target task; and 3) lower computational overhead as measured against finding solutions to each task.******Two specific target domains will be used to illustrate the approach: 1) learning policies to play soccer in the continuous valued simulated 2D world of RoboCup keepaway; 2) learning general policies for solving the 3 by 3 Rubik cube. The keepway soccer task represents a benchmark for multi-agent learning, hence has a history of previous results as well as posing tasks of incrementally increasing difficulty. The Rubik cube task has had little previous history as a benchmark for learning algorithms of any form. Instead solutions have taken the form of deploying some form of exhaustive search. Both tasks represent examples of complex task domains that have very large state-spaces (potential number of legal states), but possess underlying properties (regularities) that GP should be able to discover specific instances of. The basic hypothesis of this research is that once an instance of a context dependent strategy is identified for solving some subset of an initial task, then we should be able to use this as the basis for generalizing to many more instances of the task through a deterministic process of variation in the policy's references to the state variables. Naturally, for the process to scale, we need to avoid artificially introducing pathologies into the search. In short, the sum of initial policies from which a later policy is constructed needs to exceed the mere sum of its parts.***Success in these objectives would provide a general framework for scaling GP to a wide range of tasks with delayed payoff. Such tasks are of widespread interest to the GP community because they represent some of the most expensive, if not the most expensive, set of task domains for applying GP to. Moreover, the two task domains are widely acknowledged to be of a particularly challenging nature.**
本研究提案的总体背景是将遗传规划(GP)应用于在延迟支付环境中操作的代理(或强化学习)的学习决策策略。该提案的具体重点在于开发一个框架,以便系统地将GP扩展到比以前考虑的更困难的具有延迟回报的任务版本。我们特别感兴趣的场景是,一个简单的初始“源”任务的解决方案,然后“转移”到一个更困难但相关的(目标)任务;或者是一种迁移学习。这项工作的洞察力是利用GP的能力来识别利用状态变量子集的解决方案。然后,这为重新部署在源任务下发现的解决方案提供了基础,从而可以解决更困难的任务。采用这种方法的潜在好处是:1)不需要不断地从头开始重新发现政策;2)提高最终目标任务的成功率或更好的解决方案;3)相对于寻找每个任务的解决方案,计算开销更低。******将使用两个特定的目标域来说明该方法:1)在RoboCup keepaway的连续数值模拟二维世界中学习踢足球的策略;2)学习解3 × 3魔方的一般策略。keepway足球任务代表了多智能体学习的基准,因此具有先前结果的历史,以及提出难度逐渐增加的任务。魔方任务之前几乎没有作为任何形式的学习算法的基准。相反,解决方案采取了部署某种形式的穷举搜索的形式。这两个任务都代表了复杂任务域的示例,这些任务域具有非常大的状态空间(合法状态的潜在数量),但具有GP应该能够发现特定实例的底层属性(规则)。本研究的基本假设是,一旦上下文依赖策略的实例被确定用于解决初始任务的某些子集,那么我们应该能够将其作为基础,通过策略对状态变量引用的变化的确定性过程,推广到更多的任务实例。自然地,为了扩大这个过程的规模,我们需要避免人为地在搜索中引入病态。简而言之,构建后续策略的初始策略的总和需要超过其部分的总和。***这些目标的成功将为将GP扩展到具有延迟回报的广泛任务提供一个总体框架。这样的任务引起GP社区的广泛兴趣,因为它们代表了应用GP的一些最昂贵(如果不是最昂贵的话)的任务域集。此外,这两个任务领域被广泛认为具有特别具有挑战性的性质
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 }}
Heywood, Malcolm其他文献
Heywood, Malcolm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('Heywood, Malcolm', 18)}}的其他基金
Scaling Genetic Programming to Complex Reinforcement Learning Tasks
将遗传编程扩展到复杂的强化学习任务
- 批准号:
RGPIN-2020-04438 - 财政年份:2022
- 资助金额:
$ 1.31万 - 项目类别:
Discovery Grants Program - Individual
Scaling Genetic Programming to Complex Reinforcement Learning Tasks
将遗传编程扩展到复杂的强化学习任务
- 批准号:
RGPIN-2020-04438 - 财政年份:2021
- 资助金额:
$ 1.31万 - 项目类别:
Discovery Grants Program - Individual
Scaling Genetic Programming to Complex Reinforcement Learning Tasks
将遗传编程扩展到复杂的强化学习任务
- 批准号:
RGPIN-2020-04438 - 财政年份:2020
- 资助金额:
$ 1.31万 - 项目类别:
Discovery Grants Program - Individual
Coevolutionary automatic game content generation of physics and flighting style games
物理和飞行风格游戏的协同进化自动游戏内容生成
- 批准号:
499792-2016 - 财政年份:2018
- 资助金额:
$ 1.31万 - 项目类别:
Collaborative Research and Development Grants
Permutation based task transfer for genetic programming
基于排列的遗传编程任务转移
- 批准号:
RGPIN-2015-06117 - 财政年份:2018
- 资助金额:
$ 1.31万 - 项目类别:
Discovery Grants Program - Individual
Permutation based task transfer for genetic programming
基于排列的遗传编程任务转移
- 批准号:
RGPIN-2015-06117 - 财政年份:2017
- 资助金额:
$ 1.31万 - 项目类别:
Discovery Grants Program - Individual
Coevolutionary automatic game content generation of physics and flighting style games
物理和飞行风格游戏的协同进化自动游戏内容生成
- 批准号:
499792-2016 - 财政年份:2017
- 资助金额:
$ 1.31万 - 项目类别:
Collaborative Research and Development Grants
Permutation based task transfer for genetic programming
基于排列的遗传编程任务转移
- 批准号:
RGPIN-2015-06117 - 财政年份:2016
- 资助金额:
$ 1.31万 - 项目类别:
Discovery Grants Program - Individual
Coevolutionary automatic game content generation of physics and flighting style games
物理和飞行风格游戏的协同进化自动游戏内容生成
- 批准号:
499792-2016 - 财政年份:2016
- 资助金额:
$ 1.31万 - 项目类别:
Collaborative Research and Development Grants
Constructing risk predictors for mobile device behaviour analytics
构建移动设备行为分析的风险预测器
- 批准号:
485070-2015 - 财政年份:2015
- 资助金额:
$ 1.31万 - 项目类别:
Engage Grants Program
相似国自然基金
Data-driven Recommendation System Construction of an Online Medical Platform Based on the Fusion of Information
- 批准号:
- 批准年份:2024
- 资助金额:万元
- 项目类别:外国青年学者研究基金项目
Incentive and governance schenism study of corporate green washing behavior in China: Based on an integiated view of econfiguration of environmental authority and decoupling logic
- 批准号:
- 批准年份:2024
- 资助金额:万元
- 项目类别:外国学者研究基金项目
Exploring the Intrinsic Mechanisms of CEO Turnover and Market Reaction: An Explanation Based on Information Asymmetry
- 批准号:W2433169
- 批准年份:2024
- 资助金额:万元
- 项目类别:外国学者研究基金项目
含Re、Ru先进镍基单晶高温合金中TCP相成核—生长机理的原位动态研究
- 批准号:52301178
- 批准年份:2023
- 资助金额:30.00 万元
- 项目类别:青年科学基金项目
NbZrTi基多主元合金中化学不均匀性对辐照行为的影响研究
- 批准号:12305290
- 批准年份:2023
- 资助金额:30.00 万元
- 项目类别:青年科学基金项目
眼表菌群影响糖尿病患者干眼发生的人群流行病学研究
- 批准号:82371110
- 批准年份:2023
- 资助金额:49.00 万元
- 项目类别:面上项目
镍基UNS N10003合金辐照位错环演化机制及其对力学性能的影响研究
- 批准号:12375280
- 批准年份:2023
- 资助金额:53.00 万元
- 项目类别:面上项目
CuAgSe基热电材料的结构特性与构效关系研究
- 批准号:22375214
- 批准年份:2023
- 资助金额:50.00 万元
- 项目类别:面上项目
A study on prototype flexible multifunctional graphene foam-based sensing grid (柔性多功能石墨烯泡沫传感网格原型研究)
- 批准号:
- 批准年份:2020
- 资助金额:20 万元
- 项目类别:
基于大数据定量研究城市化对中国季节性流感传播的影响及其机理
- 批准号:82003509
- 批准年份:2020
- 资助金额:24.0 万元
- 项目类别:青年科学基金项目
相似海外基金
Development of a Novel EMG-Based Neural Interface for Control of Transradial Prostheses with Gripping Assistance
开发一种新型的基于肌电图的神经接口,用于通过抓取辅助控制经桡动脉假体
- 批准号:
10748341 - 财政年份:2024
- 资助金额:
$ 1.31万 - 项目类别:
ClinEX - Clinical Evidence Extraction, Representation, and Appraisal
ClinEX - 临床证据提取、表示和评估
- 批准号:
10754029 - 财政年份:2023
- 资助金额:
$ 1.31万 - 项目类别:
Characterizing neuroimaging 'brain-behavior' model performance bias in rural populations
表征农村人口神经影像“大脑行为”模型的表现偏差
- 批准号:
10752053 - 财政年份:2023
- 资助金额:
$ 1.31万 - 项目类别:
Investigating facilitator-driven, multi-level implementation strategies in Federally Qualified Health Centers to improve provider recommendation and HPV vaccination rates among Latino/a adolescents
调查联邦合格健康中心中促进者驱动的多层次实施策略,以提高拉丁裔/非裔青少年的医疗服务提供者推荐和 HPV 疫苗接种率
- 批准号:
10737168 - 财政年份:2023
- 资助金额:
$ 1.31万 - 项目类别:
Testing a Memory-Based Hypothesis for Anhedonia
测试基于记忆的快感缺失假设
- 批准号:
10598974 - 财政年份:2023
- 资助金额:
$ 1.31万 - 项目类别:
Development of an Online Task-Based Instructional System
基于任务的在线教学系统的开发
- 批准号:
23K02403 - 财政年份:2023
- 资助金额:
$ 1.31万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
A cloud-based digital health navigation program for colorectal cancer screening
基于云的结直肠癌筛查数字健康导航程序
- 批准号:
10697474 - 财政年份:2023
- 资助金额:
$ 1.31万 - 项目类别:
DL-based CT image formation with characterization and control of resolution and noise
基于深度学习的 CT 图像形成,具有分辨率和噪声的表征和控制
- 批准号:
10666105 - 财政年份:2023
- 资助金额:
$ 1.31万 - 项目类别:
Mechanisms underlying age-based stereotype threat effects
基于年龄的刻板印象威胁效应的潜在机制
- 批准号:
10727593 - 财政年份:2023
- 资助金额:
$ 1.31万 - 项目类别:
Towards an integrated analytics solution to creating a spatially-resolved single-cell multi-omics brain atlas
寻求集成分析解决方案来创建空间解析的单细胞多组学大脑图谱
- 批准号:
10724843 - 财政年份:2023
- 资助金额:
$ 1.31万 - 项目类别: