A Decentralized Partially Observable Decision Model for Recognizing the Multiagent Goal in Simulation Systems
Multiagent goal recognition is important in many simulation systems. Many of the existing modeling methods need detailed domain knowledge of agents’ cooperative behaviors and a training dataset to estimate policies. To solve these problems, we propose a novel decentralized partially observable decis...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2016-01-01
|
| Series: | Discrete Dynamics in Nature and Society |
| Online Access: | http://dx.doi.org/10.1155/2016/5323121 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841524800107839488 |
|---|---|
| author | Shiguang Yue Kristina Yordanova Frank Krüger Thomas Kirste Yabing Zha |
| author_facet | Shiguang Yue Kristina Yordanova Frank Krüger Thomas Kirste Yabing Zha |
| author_sort | Shiguang Yue |
| collection | DOAJ |
| description | Multiagent goal recognition is important in many simulation systems. Many of the existing modeling methods need detailed domain knowledge of agents’ cooperative behaviors and a training dataset to estimate policies. To solve these problems, we propose a novel decentralized partially observable decision model (Dec-POMDM), which models cooperative behaviors by joint policies. In this compact way, we only focus on the distribution of joint policies. Additionally, a model-free algorithm, cooperative colearning based on Sarsa, is exploited to estimate agents’ policies under the assumption of rationality, which makes the training dataset unnecessary. In the inference, considering that the Dec-POMDM is discrete and its state space is large, we implement a marginal filter (MF) under the framework of the Dec-POMDM, where the initial world states and results of actions are uncertain. In the experiments, a new scenario is designed based on the standard predator-prey problem: we increase the number of preys, and our aim is to recognize the real target of predators. Experiment results show that (a) our method recognizes goals well even when they change dynamically; (b) the Dec-POMDM outperforms supervised trained HMMs in terms of precision, recall, and F-measure; and (c) the MF infers goals more efficiently than the particle filter under the framework of the Dec-POMDM. |
| format | Article |
| id | doaj-art-b297a543c2c44bc68269570856d8373b |
| institution | Kabale University |
| issn | 1026-0226 1607-887X |
| language | English |
| publishDate | 2016-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Discrete Dynamics in Nature and Society |
| spelling | doaj-art-b297a543c2c44bc68269570856d8373b2025-02-03T05:47:21ZengWileyDiscrete Dynamics in Nature and Society1026-02261607-887X2016-01-01201610.1155/2016/53231215323121A Decentralized Partially Observable Decision Model for Recognizing the Multiagent Goal in Simulation SystemsShiguang Yue0Kristina Yordanova1Frank Krüger2Thomas Kirste3Yabing Zha4College of Information System and Management, National University of Defense Technology, Changsha 410073, ChinaInstitute of Computer Science, University of Rostock, 18051 Rostock, GermanyInstitute of Computer Science, University of Rostock, 18051 Rostock, GermanyInstitute of Computer Science, University of Rostock, 18051 Rostock, GermanyCollege of Information System and Management, National University of Defense Technology, Changsha 410073, ChinaMultiagent goal recognition is important in many simulation systems. Many of the existing modeling methods need detailed domain knowledge of agents’ cooperative behaviors and a training dataset to estimate policies. To solve these problems, we propose a novel decentralized partially observable decision model (Dec-POMDM), which models cooperative behaviors by joint policies. In this compact way, we only focus on the distribution of joint policies. Additionally, a model-free algorithm, cooperative colearning based on Sarsa, is exploited to estimate agents’ policies under the assumption of rationality, which makes the training dataset unnecessary. In the inference, considering that the Dec-POMDM is discrete and its state space is large, we implement a marginal filter (MF) under the framework of the Dec-POMDM, where the initial world states and results of actions are uncertain. In the experiments, a new scenario is designed based on the standard predator-prey problem: we increase the number of preys, and our aim is to recognize the real target of predators. Experiment results show that (a) our method recognizes goals well even when they change dynamically; (b) the Dec-POMDM outperforms supervised trained HMMs in terms of precision, recall, and F-measure; and (c) the MF infers goals more efficiently than the particle filter under the framework of the Dec-POMDM.http://dx.doi.org/10.1155/2016/5323121 |
| spellingShingle | Shiguang Yue Kristina Yordanova Frank Krüger Thomas Kirste Yabing Zha A Decentralized Partially Observable Decision Model for Recognizing the Multiagent Goal in Simulation Systems Discrete Dynamics in Nature and Society |
| title | A Decentralized Partially Observable Decision Model for Recognizing the Multiagent Goal in Simulation Systems |
| title_full | A Decentralized Partially Observable Decision Model for Recognizing the Multiagent Goal in Simulation Systems |
| title_fullStr | A Decentralized Partially Observable Decision Model for Recognizing the Multiagent Goal in Simulation Systems |
| title_full_unstemmed | A Decentralized Partially Observable Decision Model for Recognizing the Multiagent Goal in Simulation Systems |
| title_short | A Decentralized Partially Observable Decision Model for Recognizing the Multiagent Goal in Simulation Systems |
| title_sort | decentralized partially observable decision model for recognizing the multiagent goal in simulation systems |
| url | http://dx.doi.org/10.1155/2016/5323121 |
| work_keys_str_mv | AT shiguangyue adecentralizedpartiallyobservabledecisionmodelforrecognizingthemultiagentgoalinsimulationsystems AT kristinayordanova adecentralizedpartiallyobservabledecisionmodelforrecognizingthemultiagentgoalinsimulationsystems AT frankkruger adecentralizedpartiallyobservabledecisionmodelforrecognizingthemultiagentgoalinsimulationsystems AT thomaskirste adecentralizedpartiallyobservabledecisionmodelforrecognizingthemultiagentgoalinsimulationsystems AT yabingzha adecentralizedpartiallyobservabledecisionmodelforrecognizingthemultiagentgoalinsimulationsystems AT shiguangyue decentralizedpartiallyobservabledecisionmodelforrecognizingthemultiagentgoalinsimulationsystems AT kristinayordanova decentralizedpartiallyobservabledecisionmodelforrecognizingthemultiagentgoalinsimulationsystems AT frankkruger decentralizedpartiallyobservabledecisionmodelforrecognizingthemultiagentgoalinsimulationsystems AT thomaskirste decentralizedpartiallyobservabledecisionmodelforrecognizingthemultiagentgoalinsimulationsystems AT yabingzha decentralizedpartiallyobservabledecisionmodelforrecognizingthemultiagentgoalinsimulationsystems |