Language inference with multi-head automata through reinforcement learning

Name: Language inference with multi-head automata through reinforcement learning
Author: Şekerci, Alper, Köken, Özlem Salehi

İsim	Language inference with multi-head automata through reinforcement learning
Yazar	Şekerci, Alper, Köken, Özlem Salehi
Basım Tarihi:	2020
Basım Yeri	- IEEE
Konu	Finite automata, Reinforcement learning, Neural network, Q-learning, Genetic algorithm
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-172816926-2
Kayıt Numarası	e5584292-b830-456c-98b3-34a920f79db4
Lokasyon	Computer Science
Tarih	2020
Örnek Metin	The purpose of this paper is to use reinforcement learning to model learning agents which can recognize formal languages. Agents are modeled as simple multi-head automaton, a new model of finite automaton that uses multiple heads, and six different languages are formulated as reinforcement learning problems. Two different algorithms are used for optimization. First algorithm is Q-learning which trains gated recurrent units to learn optimal policies. The second one is genetic algorithm which searches for the optimal solution by using evolution-inspired operations. The results show that genetic algorithm performs better than Q-learning algorithm in general but Q-learning algorithm finds solutions faster for regular languages.
DOI	10.1109/IJCNN48605.2020.9207156

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Language inference with multi-head automata through reinforcement learning

Yazar Şekerci, Alper, Köken, Özlem Salehi

Basım Tarihi 2020

Basım Yeri - IEEE

Konu Finite automata, Reinforcement learning, Neural network, Q-learning, Genetic algorithm

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-172816926-2

Kayıt Numarası e5584292-b830-456c-98b3-34a920f79db4

Lokasyon Computer Science

Tarih 2020

Örnek Metin The purpose of this paper is to use reinforcement learning to model learning agents which can recognize formal languages. Agents are modeled as simple multi-head automaton, a new model of finite automaton that uses multiple heads, and six different languages are formulated as reinforcement learning problems. Two different algorithms are used for optimization. First algorithm is Q-learning which trains gated recurrent units to learn optimal policies. The second one is genetic algorithm which searches for the optimal solution by using evolution-inspired operations. The results show that genetic algorithm performs better than Q-learning algorithm in general but Q-learning algorithm finds solutions faster for regular languages.

DOI 10.1109/IJCNN48605.2020.9207156