TY - JOUR
T1 - Discovering underlying plans based on shallow models
AU - Zhuo, Hankz Hankui
AU - Zha, Yantian
AU - Kambhampati, Subbarao
AU - Tian, Xin
N1 - Funding Information:
Zhuo thanks the support of the National Natural Science Foundation of China (U1611262), Guangdong Natural Science Fund for Distinguished Young Scholars (2017A030306028), Guangdong special branch plans young talent with scientific and technological innovation, Pearl River Science and Technology New Star of Guangzhou, and Guangdong Province Key Laboratory of Big Data Analysis and Processing for the support of this research. Kambhampati’s research is supported in part by the ONR grants N00014-16-1-2892, N00014-18-1-2442, N00014-18-1-2840, the AFOSR grant FA9550-18-1-0067, and the NASA grant NNX17AD06G. Authors’ addresses: H. H. Zhuo (corresponding author) and X. Tian, School of Data and Computer Science, Sun Yat-Sen University, Guangzhou, China and Key Laboratory of Machine Intelligence and Advanced Computing (Sun Yat-Sen University) Ministry of Education, China; emails: zhuohank@mail.sysu.edu.cn, tianxin1860@gmail.com; Y. Zha and S. Kambhampati, School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ 85281 USA; emails: {yzha3, rao}@asu.edu. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. © 2020 Association for Computing Machinery. 2157-6904/2020/01-ART18 $15.00 https://doi.org/10.1145/3368270
Publisher Copyright:
© 2020 Association for Computing Machinery.
PY - 2020/1
Y1 - 2020/1
N2 - Plan recognition aims to discover target plans (i.e., sequences of actions) behind observed actions, with history plan libraries or action models in hand. Previous approaches either discover plans by maximally “matching” observed actions to plan libraries, assuming target plans are from plan libraries, or infer plans by executing action models to best explain the observed actions, assuming that complete action models are available. In real-world applications, however, target plans are often not from plan libraries, and complete action models are often not available, since building complete sets of plans and complete action models are often difficult or expensive. In this article, we view plan libraries as corpora and learn vector representations of actions using the corpora; we then discover target plans based on the vector representations. Specifically, we propose two approaches, DUP and RNNPlanner, to discover target plans based on vector representations of actions. DUP explores the EM-style (Expectation Maximization) framework to capture local contexts of actions and discover target plans by optimizing the probability of target plans, while RNNPlanner aims to leverage long-short term contexts of actions based on RNNs (Recurrent Neural Networks) framework to help recognize target plans. In the experiments, we empirically show that our approaches are capable of discovering underlying plans that are not from plan libraries without requiring action models provided. We demonstrate the effectiveness of our approaches by comparing its performance to traditional plan recognition approaches in three planning domains. We also compare DUP and RNNPlanner to see their advantages and disadvantages.
AB - Plan recognition aims to discover target plans (i.e., sequences of actions) behind observed actions, with history plan libraries or action models in hand. Previous approaches either discover plans by maximally “matching” observed actions to plan libraries, assuming target plans are from plan libraries, or infer plans by executing action models to best explain the observed actions, assuming that complete action models are available. In real-world applications, however, target plans are often not from plan libraries, and complete action models are often not available, since building complete sets of plans and complete action models are often difficult or expensive. In this article, we view plan libraries as corpora and learn vector representations of actions using the corpora; we then discover target plans based on the vector representations. Specifically, we propose two approaches, DUP and RNNPlanner, to discover target plans based on vector representations of actions. DUP explores the EM-style (Expectation Maximization) framework to capture local contexts of actions and discover target plans by optimizing the probability of target plans, while RNNPlanner aims to leverage long-short term contexts of actions based on RNNs (Recurrent Neural Networks) framework to help recognize target plans. In the experiments, we empirically show that our approaches are capable of discovering underlying plans that are not from plan libraries without requiring action models provided. We demonstrate the effectiveness of our approaches by comparing its performance to traditional plan recognition approaches in three planning domains. We also compare DUP and RNNPlanner to see their advantages and disadvantages.
KW - Action representation
KW - Plan recognition
KW - Recurrent neural networks
KW - Shallow model
UR - http://www.scopus.com/inward/record.url?scp=85079488052&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85079488052&partnerID=8YFLogxK
U2 - 10.1145/3368270
DO - 10.1145/3368270
M3 - Article
AN - SCOPUS:85079488052
SN - 2157-6904
VL - 11
JO - ACM Transactions on Intelligent Systems and Technology
JF - ACM Transactions on Intelligent Systems and Technology
IS - 2
M1 - 18
ER -