Uncertainty, Action & Interaction: in Pursuit of Cognitive Information Processing

不确定性，行动

• 批准号: 121634-2013
• 负责人: Chaibdraa, Brahim
• 金额: $ 2.19万
• 依托单位: Université Laval
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2016
• 资助国家: 加拿大
• 起止时间: 2016-01-01 至 2017-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=593322
• 关键词: Uncertainty; Action; Interaction; Pursuit; Cognitive

My research vision aims to contribute to the design and implementation of profound cognitive information processing (CIP) systems for augmented human cognition in real-life environments. CIP involves the ability to perceive, learn, reason and interact robustly in face of uncertainty and noise. I plan to build on my previous work to elaborate efficient algorithms to tackle different cognitive levels from low to high-level sustaining CIP systems: (i) reasoning on uncertain knowledge in static worlds; (ii) reasoning over time in an uncertain environment; (iii) deciding what to do in uncertain environment; (iv) deciding what to do in an uncertain and multiagent environment. In the context of (i), we propose to construct our own priors so that one can cover directed acyclic graph structures as belief networks and latent trees. We particularly investigate which representation of the posterior distribution over hidden units' popularity is the best. In the context of (ii), our work will mainly focus on the interaction between modelling and filtering in a Bayesian perspective. One direction aims at applying flexible Bayesian nonparametric modelling methods to learn unknown probabilistic models for hidden state estimation. The other direction is to design a recursive Bayesian filtering framework to efficiently update Bayesian nonparametric modelling performance in an online manner. For level (iii), we will first investigate the case of transfer learning in the context of Bayesian partially observable Markov decision process (POMDP), particularly (a) when multi-task and life-learning are used for learning a POMDP and (b) when the training data from single task are not sufficient. Second, we investigate a more speculative avenue which consists in structuring Bayesian POMDP in the form of dynamic decision network (DDN), that is, a DBN completed by rewards, and then translate it to an inference problem. Finally and for (iv), we will focus on how several aspects of cooperative control, particularly consensus between agents, can be formulated in ``potential games'' and how these specific games can be pertained to distributed resource allocation as well as to local and distributed control laws.

我的研究愿景旨在为在现实生活环境中增强人类认知的深刻认知信息处理(CIP)系统的设计和实现做出贡献。CIP包括在面对不确定性和噪声时稳健地感知、学习、推理和互动的能力。我计划在我以前工作的基础上，详细阐述有效的算法，以解决从低水平到高级持续CIP系统的不同认知水平：(I)在静态世界中对不确定知识进行推理；(Ii)在不确定环境中随着时间的推移进行推理；(Iii)在不确定环境中决定做什么；(Iv)决定在不确定和多代理环境中做什么。在(I)的背景下，我们建议构造我们自己的先验，这样就可以将有向无环图结构覆盖为信任网络和潜在树。我们特别研究了隐藏单元受欢迎度的后验分布的哪种表示是最好的。在(Ii)的背景下，我们的工作将主要集中在贝叶斯观点中建模和过滤之间的相互作用。一个方向是应用灵活的贝叶斯非参数建模方法来学习未知的概率模型以进行隐藏状态估计。另一个方向是设计递归贝叶斯过滤框架，以在线方式高效地更新贝叶斯非参数建模性能。对于水平(III)，我们将首先在贝叶斯部分可观测马尔可夫决策过程(POMDP)的背景下研究转移学习的情况，特别是(A)当多任务和生活学习用于学习POMDP时，以及(B)当来自单个任务的训练数据不充分时。其次，我们研究了一种更具投机性的途径，即以动态决策网络(DDN)的形式构造贝叶斯POMDP，即由奖励完成的DBN，然后将其转化为推理问题。最后，对于(Iv)，我们将重点讨论如何在“潜在博弈”中制定合作控制的几个方面，特别是代理人之间的共识，以及这些具体博弈如何与分布式资源分配以及本地和分布式控制法有关。