Back to Search

Language inference with multi-head automata through reinforcement learning

Title	Language inference with multi-head automata through reinforcement learning
Author	Şekerci, Alper, Köken, Özlem Salehi
Publication Date:	2020
Publication Place	- IEEE
Subject	Finite automata, Reinforcement learning, Neural network, Q-learning, Genetic algorithm
Type	Document
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	978-172816926-2
Record ID	e5584292-b830-456c-98b3-34a920f79db4
Library Location	Computer Science
Date	2020
Sample Text	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

View in source Özyeğin University Özyeğin University - Historical works, archives, and periodicals search engine

Özyeğin University

Language inference with multi-head automata through reinforcement learning

Author Şekerci, Alper, Köken, Özlem Salehi

Publication Date 2020

Publication Place - IEEE

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

Type Document

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 978-172816926-2

Record ID e5584292-b830-456c-98b3-34a920f79db4

Library Location Computer Science

Date 2020

Sample Text 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