Reinforcement learning in a virtual world: a study of ppo and sac within unity ML agents

Rufat Mammadzada

Кимёвий технология. Назорат ва бошқарув · 2025-yil

Annotatsiya

This study explores the use of Unity3D as a versatile platform for developing, training, and evaluating intelligent agents through reinforcement learning. Leveraging the Unity ML-Agents Toolkit, a dynamic 3D environment was created to examine agent learning behavior using two advanced algorithms: Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC). The simulation environment consisted of navigable terrain bounded by red borders, with collectible blue balls serving as rewards and a purple cube representing the agent. A carefully designed reward system was implemented to encourage goal-directed behavior and penalize inefficiency, while time constraints introduced an additional challenge requiring both precision and speed. Through iterative training and refinement, the agent demonstrated increasingly complex behaviors, such as path optimization and efficient resource collection. Comparative analysis revealed that SAC exhibited rapid initial learning but suffered from performance instability due to excessive exploration, while PPO showed slower convergence but achieved more stable and consistent long-term results. The findings highlight Unity’s potential as a comprehensive simulation and experimentation framework, bridging the gap between real-time visualization and machine learning. Beyond game development, this approach can be extended to applications in robotics, industrial automation, and intelligent system design, offering an accessible yet powerful environment for studying adaptive, autonomous behaviors in virtual settings.

Maqola ma’lumotlari
MualliflarRufat Mammadzada
JurnalКимёвий технология. Назорат ва бошқарув
NashriyotТошкент давлат техника университети, «Ўзқурилишматериаллар» ДАК, «Ўзкимёсаноат» ДАК, «Совпластитал» ҚҚ, Ўзбекистон Интеллектуал мулк агентлиги
ISSN2181-1105, 1815-4840
Nashr sanasi2025-11-01
Jild2025
Son5
Betlar96-103
TilIngliz
Ilmiy sohaTexnika
DOI10.59048/2181-1105.1722
Indeksga qo‘shilgan2026-09-02

DOI: 10.59048/2181-1105.1722 · Maqolaning asl sahifasi

Ilmiy soha

Texnika

Iqtibos keltirish

APARufat Mammadzada (2025). REINFORCEMENT LEARNING IN A VIRTUAL WORLD: A STUDY OF PPO AND SAC WITHIN UNITY ML AGENTS. Кимёвий технология. Назорат ва бошқарув, 2025(5), 96-103. https://doi.org/10.59048/2181-1105.1722
GOST (OAK)Rufat Mammadzada REINFORCEMENT LEARNING IN A VIRTUAL WORLD: A STUDY OF PPO AND SAC WITHIN UNITY ML AGENTS // Кимёвий технология. Назорат ва бошқарув. – 2025. – T. 2025, № 5. – P. 96-103. – DOI: 10.59048/2181-1105.1722.
MLARufat Mammadzada. “REINFORCEMENT LEARNING IN A VIRTUAL WORLD: A STUDY OF PPO AND SAC WITHIN UNITY ML AGENTS.” Кимёвий технология. Назорат ва бошқарув, 2025(5), 96-103, 2025. https://doi.org/10.59048/2181-1105.1722
ChicagoRufat Mammadzada. “REINFORCEMENT LEARNING IN A VIRTUAL WORLD: A STUDY OF PPO AND SAC WITHIN UNITY ML AGENTS.” Кимёвий технология. Назорат ва бошқарув, 2025(5), 96-103 (2025). https://doi.org/10.59048/2181-1105.1722
HarvardRufat Mammadzada (2025) ‘REINFORCEMENT LEARNING IN A VIRTUAL WORLD: A STUDY OF PPO AND SAC WITHIN UNITY ML AGENTS’, Кимёвий технология. Назорат ва бошқарув, 2025(5), 96-103. https://doi.org/10.59048/2181-1105.1722
BibTeX
@article{rufatmammadzada2025,
  title = {REINFORCEMENT LEARNING IN A VIRTUAL WORLD: A STUDY OF PPO AND SAC WITHIN UNITY ML AGENTS},
  author = {Rufat Mammadzada},
  journal = {Кимёвий технология. Назорат ва бошқарув},
  year = {2025},
  volume = {2025},
  number = {5},
  pages = {96-103},
  doi = {10.59048/2181-1105.1722},
  url = {https://doi.org/10.59048/2181-1105.1722}
}

Boshqa maqola uchun iqtibos tayyorlash

Кимёвий технология. Назорат ва бошқарув jurnalidan boshqa maqolalar

Кимёвий технология. Назорат ва бошқарув — barcha maqolalar · 2025-yil arxivi

Texnika sohasidagi boshqa maqolalar

Texnika sohasidagi OAK jurnallari