Şekerci, AlperKöken, Özlem Salehi2021-06-142021-06-142020978-172816926-2http://hdl.handle.net/10679/7432https://doi.org/10.1109/IJCNN48605.2020.9207156The 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.engrestrictedAccessconferenceObject00062602140406210.1109/IJCNN48605.2020.9207156Finite automataReinforcement learningNeural networkQ-learningGenetic algorithm2-s2.0-85093867777