Claim Missing Document
Check
Articles

Found 2 Documents
Search

Optimalisasi Model Bahasa dan Sistem Ekonomi Berbasis Teks dengan Proximal Policy Optimization: Studi Kasus dalam NLP Modern Darmawan, Irwan; Ramadhani, Nilam; Nazir Arifin, Mohammad; -, Ubaidi; Puspa Dewi, Nindian; Innuddin, Muhammad
Jurnal Bumigora Information Technology (BITe) Vol. 7 No. 1 (2025)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/bite.v7i1.5222

Abstract

Background: This study investigates the use of the Proximal Policy Optimization (PPO) algorithm in two text-based case studies: alignment of large language models (LLMs) with human preferences and dynamic pricing based on customer reviews. In the LLM case, PPO combined with preference-based learning significantly improves alignment, BLEU, and human-likeness scores.Objective: This research aims to evaluate PPO’s effectiveness in text-based decision-making through these two cases.Methods: The method employed is reinforcement learning experimentation using the PPO approach. For the LLM case, PPO is integrated with preference learning to enhance alignment, BLEU, and human-like output. Meanwhile, in the economic scenario, PPO produces adaptive pricing strategies with high accuracy or low Mean Absolute Error (MAE) and the best cumulative rewards, outperforming the A3C and DDPG algorithms. Cross-validation and ablation studies assessed PPO’s generalization capability and the contribution of reward components, clipping, and exploration strategies.Result: The findings demonstrate that PPO excels across distinct domains and offers a stable and efficient solution for text-based tasks.Conclusion: The findings confirm its flexibility for various NLP applications and intelligent decision-making systems 
Psychological Assistance for Elderly Communities in Toket Village, Pamekasan Trisanti, Yuliana; Nazir Arifin, Mohammad
Jurnal Pengabdian Indonesia Vol. 2 No. 1 (2024): Desember
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/jpi.v2i1.3637

Abstract

The abstract The ultimate goal of every development boils down to improving the quality of human resources (HR). Human resources are both the subject and object of development, covering the entire human life cycle, from conception to the end of life. Therefore, the development of human quality must be an important concern. Based on the cycle above, it is necessary to make an effort to provide an alternative solution that can improve the performance of posbindu and activate sub-districts that do not yet have posbindu for the elderly, as well as increasing the happiness of the elderly group. Apart from that, activities are needed that can increase enthusiasm, skills and care for the elderly to provide comfort and happiness at the end of their lives. With technology transfer, the community provides genotyric care training for Posbindu cadres as partner communities. Therefore, accompanied by counseling activities and training on useful genotyric care, it can be effective, meaning that the training can be carried out for local elderly people who in turn can provide happiness and health for members of the elderly group as partners.