Salam, rekan Nawala! Semoga kalian selalu dalam keadaan sehat.
Ini adalah Nawala IAES dari Institute of Advanced Engineering and Science. Hari ini kami ingin berbagi wawasan yang bertemakan teknologi reinforcement learning (RL). RL merupakan salah satu cabang dalam konsep deep learning yang dapat membantu dalam memberikan hasil gabungan menjadi lebih baik. Menurut Radha dkk., pengimplementasian algoritma RL berpotensi memberikan hasil yang lebih baik daripada tidak menggunakannya. Sehingga implementasi RL dapat berjalan lebih fleksibel di lingkungan yang lebih beragam. Lebih lengkapnya dapat dibaca pada artikel berikut:
Reinforcement learning is considered as a machine learning technique that is anxious with software agents should behave in particular environment. Reinforcement learning (RL) is a division of deep learning concept that assists you to make best use of some part of the collective return. In this paper evolving reinforcement learning algorithms shows possible to learn a fresh and understable concept by using a graph representation and applying optimization methods from the auto machine learning society. In this observe, we stand for the loss function, it is used to optimize an agent’s parameter in excess of its knowledge, as an imputational graph, and use traditional evolution to develop a population of the imputational graphs over a set of uncomplicated guidance environments. These outcomes in gradually better RL algorithms and the exposed algorithms simplify to more multifaceted environments, even though with visual annotations.
The general design of the automation for multiple fields using reinforcement learning algorithm
Vijaya Kumar Reddy Radha, Anantha N. Lakshmipathi, Ravi Kumar Tirandasu, Paruchuri Ravi Prakash
Pengembangan teknologi reinforcement learning merambah kearah prediksi pasar valuta asing. Penelitian yang dilakukan oleh Jamali dkk. mengimplementasikan RL untuk membantu memprediksi fluktuasi nilai tukar dari pasar valuta asing. Hasil dari penelitian tersebut dapat mengetahui dan menentukan kapan waktu yang tepat untuk berinvestasi dengan membeli, atau menjual, dan ini melalui tren pasangan mata uang yang tercatat atau terprediksi. Hasil lengkap terkait penelitian ini dapat dilihat pada artikel berikut:
Foreign exchange market refers to the market in which currencies from around the world are traded. It allows investors to buy or sell a currency of their choice. Forex interests several categories of stakeholders, such as companies that carry out international contracts, large institutional investors, via the main banks, which carry out transactions on this market for speculative purposes. One of the most important aspects in the Forex market is knowing when to invest by buying, selling, and this through the recorded trend of a currency pair, but given the characteristics of the Forex market namely its chaotic, noisy and not stationary nature, prediction becomes a big challenge for traders when it comes to predicting accuracy. This paper aims to predict the right action to be taken at a certain moment through the development of a model that combines multiple techniques such multiple regression, simulated annealing meta-heuristics, reinforcement learning and technical indicators.
Hybrid Forex prediction model using multiple regression, simulated annealing, reinforcement learning and technical analysis
Hana Jamali, Younes Chihab, Iván García-Magariño, Omar Bencharef
Yazid dan Rachmawati mengembangkan autonomous driving yang dikombinasikan dengan RL. Dalam penelitiannya, mereka menjelaskan sistem penggerak otonom yang bertujuan agar mobil dapat bergerak tanpa pengemudi dan tidak menimbulkan kecelakaan. Penelitian ini dikatakan berhasil jika memenuhi tiga syarat, yaitu: i) mobil tidak boleh menabrak tembok; ii) mobil mencapai tujuan; iii) mobil mencapai tujuan dalam kondisi yang tidak boleh ditabrak, seperti jalur pejalan kaki, gedung, atau kendaraan lain. Lebih lengkap terkait penelitian ini dapat dilihat pada artikel berikut:
Autonomous driving is one solution that can minimize and even prevent accidents. In autonomous driving, the vehicle must know the surrounding environment and move under the provisions and situations. We build an autonomous driving system using proximal policy optimization (PPO) in deep reinforcement learning, with PPO acting as an instinct for the agent to choose an action. The instinct will be updated continuously until the agent reaches the destination from the initial point. We use five sensory inputs for the agent to accelerate, turn the steer, hit the brakes, avoid the walls, detect the initial point, and reach the destination point. We evaluated our proposed autonomous driving system in a simulation environment with several branching tracks, reflecting a real-world setting. For our driving simulation purpose in this research, we use the Unity3D engine to construct the dataset (in the form of a road track) and the agent model (in the form of a car). Our experimental results firmly indicate our agent can successfully control a vehicle to navigate to the destination point.
Autonomous driving system using proximal policy optimization in deep reinforcement learning
Imam Noerhenda Yazid, Ema Rachmawati
Beberapa artikel diatas merupakan bagian kecil dari penelitian mengenai pengembangan reinforcement learning. Untuk mendapatkan informasi lebih lanjut silahkan kunjungi secara GRATIS pada link berikut: https://ijai.iaescore.com/ dan https://ijeecs.iaescore.com/.
Redaksi: I. Busthomi