Iranian Journal of Fuzzy Systems، جلد ۱۲، شماره ۵، صفحات ۹۹-۱۱۶
عنوان فارسی
چکیده فارسی مقاله
کلیدواژه‌های فارسی مقاله
عنوان انگلیسی Hierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
چکیده انگلیسی مقاله This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed to have different representations of an environment while having similar actions. The learning framework is $Q$-learning. Each dimension of the functional space is the normalized expected value of an action. An unsupervisedclustering approach is used to form the functional concepts as some fuzzy areas in the functional space. The functional concepts are abstracted further in a hierarchy using the clustering approach. The hierarchical concepts are employed for knowledge transfer among agents. Properties of the proposed approach are tested in a set of case studies. The results show that the approach is very effective in transfer learning among heterogeneous agents especially in the beginning episodes of the learning.
کلیدواژه‌های انگلیسی مقاله
نویسندگان مقاله a موسوی |
control and intelligent processing center of excellence, school of electrical and computer engineering, university of tehran, tehran, iran
سازمان اصلی تایید شده: دانشگاه تهران (Tehran university)

m نیلی احمدآبادی | nili ahmadabadi
control and intelligent processing center of excellence, school of electrical and computer engineering, university of tehran, tehran, iran and school of cognitive science, institute for research in fundamental sciences ipm , tehran, iran
سازمان اصلی تایید شده: دانشگاه تهران (Tehran university)

h vosoughpour |
control and intelligent processing center of excellence, school of electrical and computer engineering, university of tehran, tehran, iran
سازمان اصلی تایید شده: دانشگاه تهران (Tehran university)

بی بی نرگس اعرابی | b n
control and intelligent processing center of excellence, school of electrical and computer engineering, university of tehran, tehran, iran and school of cognitive science, institute for research in fundamental sciences ipm , tehran, iran
سازمان اصلی تایید شده: دانشگاه تهران (Tehran university)

n زارع |
control and intelligent processing center of excellence, school of electrical and computer engineering, university of tehran, tehran, iran
سازمان اصلی تایید شده: دانشگاه تهران (Tehran university)

نشانی اینترنتی http://ijfs.usb.ac.ir/article_2113_282ba69af4a0a581fecc56675062be1d.pdf
فایل مقاله اشکال در دسترسی به فایل - ./files/site1/rds_journals/448/article-448-131678.pdf
کد مقاله (doi)
زبان مقاله منتشر شده en
موضوعات مقاله منتشر شده
نوع مقاله منتشر شده
برگشت به: صفحه اول پایگاه   |   نسخه مرتبط   |   نشریه مرتبط   |   فهرست نشریات