Fast Reinforcement Learning Using Multiple Models and State Decomposition
Fast Reinforcement Learning Using Multiple Models and State Decomposition
批准号:
1407925
负责人:
Snehasis Mukhopadhyay
金额:
$15.42万
依托单位:
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2014
资助国家:
美国
项目状态:
已结题
起止时间:
2014-08-15 至 2017-07-31
中文摘要
该项目试图为强化学习和近似动态规划(RLADP)开发更好的方法,以便能够处理在时间和空间上都更复杂的决策任务。强化学习系统是一种系统,它可以基于观察环境、对环境采取行动和接收性能反馈的经验,学习最大限度地提高性能或满意度,类似于用于强化动物行为的痛苦或快乐。当环境在空间或时间上过于复杂时,现有的强化学习方法学习速度不够快,不能很好地执行。这个项目将开发新的方法来处理这种复杂性。该团队还将与IBM合作研究,并试图解决涉及插电式混合动力汽车车队管理的试验台问题。复杂性将通过使用多模型方法来处理,通过评估和更新标志着状态空间不同区域之间转换的标志性状态来连接各种选项或技能。这类似于之前在PI的学习和自适应系统研讨会上提出的关于决策块和修改的Bellman方程的工作,但在其他方面是一个独特的、新的重要方向。基于一种空间分解的多智能体方法解决了空间中的复杂性。
英文摘要
This project attempts to develop better methods for Reinforcement Learning and Approximate Dynamic Programming (RLADP), in order to be able to handle decision tasks with greater complexity both in time and in space. Reinforcement learning systems are systems which can learn to maximize any measure of performance or satisfaction, based on their experience of observing their environment, acting on the environment, and receiving feedback on performance, similar to the pain or pleasure which is used to reinforce animal behavior. Current reinforcement learning methods do not learn fast enough to perform well, when their environment is too complex in space or in time. This project will develop new methods to handle that kind of complexity. The team will also have a collaboration with IBM research, and will try to address a testbed problem involving the management of a fleet of plug-in hybrid cars.Complexity in time will be handled by use of a multiple model approach, connecting various options or skills by evaluation and updating of the landmark states which mark transitions between different regions of state space. This is similar to previous work on decision blocks and modified Bellman equations previously presented at the PI's workshop on learning and adaptive systems, but otherwise is a unique, new an important direction. Complexity in space is addressed by a multiagent approach, based on a kind of spatial decomposition.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Collaborative Research: Mutual Learning: A Systems Theoretic Investigation
-
批准号:1930606
-
项目类别:Standard Grant
-
资助金额:$26.86万
-
财政年份:2019
-
负责人:Snehasis Mukhopadhyay
-
依托单位:
ITR: An Active, Personalized, Adaptive, Multi-format Biological Information Delivery System
-
批准号:0081944
-
项目类别:Continuing Grant
-
资助金额:$49.43万
-
财政年份:2000
-
负责人:Snehasis Mukhopadhyay
-
依托单位:
Career: Adaptation and Learning in Distributed Systems Using Neural Networks
-
批准号:9623971
-
项目类别:Continuing Grant
-
资助金额:$33.22万
-
财政年份:1996
-
负责人:Snehasis Mukhopadhyay
-
依托单位:
国内基金
海外基金
海桑属杂种区强化(Reinforcement)的检验与遗传基础研究
-
批准号:30800060
-
项目类别:青年科学基金项目
-
资助金额:23.0万元
-
批准年份:2008
-
负责人:周仁超
-
依托单位: