Reinforcement Learning-Based Autonomous Soccer Agents: A Study in Multi-Agent Coordination and Strategy Development
Reinforcement learning (RL) approaches, particularly Q-learning, have emerged as strong tools for autonomous agent training, allowing agents to acquire optimum decision-making rules through interaction with their surroundings. This research investigates the use of Q-learning in the context of traini...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Buana Perjuangan Karawang
2025-01-01
|
| Series: | Buana Information Technology and Computer Sciences |
| Subjects: | |
| Online Access: | https://journal.ubpkarawang.ac.id/index.php/bit-cs/article/view/7270 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576016624648192 |
|---|---|
| author | Biplov Paneru Bishwash Paneru Ramhari Poudyal Khem Poudyal |
| author_facet | Biplov Paneru Bishwash Paneru Ramhari Poudyal Khem Poudyal |
| author_sort | Biplov Paneru |
| collection | DOAJ |
| description | Reinforcement learning (RL) approaches, particularly Q-learning, have emerged as strong tools for autonomous agent training, allowing agents to acquire optimum decision-making rules through interaction with their surroundings. This research investigates the use of Q-learning in the context of training autonomous agents for robotic soccer, a complex and dynamic arena that necessitates strategic planning, coordination, and adaptation. We studied the learning progress and performance of agents taught using Q-learning in a series of experiments carried out in a simulated soccer setting. During training, agents interacted with the soccer environment, iteratively changing their Q-values in response to observable rewards and behaviors. Despite the high-dimensional and stochastic character of the soccer domain, Q-learning helped the agents develop excellent tactics and decision-making capabilities. Notably, our study found that, on average, the agents required 64 steps to reach a stable policy with an average reward of -1. |
| format | Article |
| id | doaj-art-cedff336e4964cb38db0f9e4a702f433 |
| institution | Kabale University |
| issn | 2715-2448 2715-7199 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Universitas Buana Perjuangan Karawang |
| record_format | Article |
| series | Buana Information Technology and Computer Sciences |
| spelling | doaj-art-cedff336e4964cb38db0f9e4a702f4332025-01-31T15:07:54ZengUniversitas Buana Perjuangan KarawangBuana Information Technology and Computer Sciences2715-24482715-71992025-01-0161101710.36805/bit-cs.v6i1.72707270Reinforcement Learning-Based Autonomous Soccer Agents: A Study in Multi-Agent Coordination and Strategy DevelopmentBiplov PaneruBishwash PaneruRamhari PoudyalKhem PoudyalReinforcement learning (RL) approaches, particularly Q-learning, have emerged as strong tools for autonomous agent training, allowing agents to acquire optimum decision-making rules through interaction with their surroundings. This research investigates the use of Q-learning in the context of training autonomous agents for robotic soccer, a complex and dynamic arena that necessitates strategic planning, coordination, and adaptation. We studied the learning progress and performance of agents taught using Q-learning in a series of experiments carried out in a simulated soccer setting. During training, agents interacted with the soccer environment, iteratively changing their Q-values in response to observable rewards and behaviors. Despite the high-dimensional and stochastic character of the soccer domain, Q-learning helped the agents develop excellent tactics and decision-making capabilities. Notably, our study found that, on average, the agents required 64 steps to reach a stable policy with an average reward of -1.https://journal.ubpkarawang.ac.id/index.php/bit-cs/article/view/7270q-learningrewardreinforcement learningoccer agents |
| spellingShingle | Biplov Paneru Bishwash Paneru Ramhari Poudyal Khem Poudyal Reinforcement Learning-Based Autonomous Soccer Agents: A Study in Multi-Agent Coordination and Strategy Development Buana Information Technology and Computer Sciences q-learning reward reinforcement learning occer agents |
| title | Reinforcement Learning-Based Autonomous Soccer Agents: A Study in Multi-Agent Coordination and Strategy Development |
| title_full | Reinforcement Learning-Based Autonomous Soccer Agents: A Study in Multi-Agent Coordination and Strategy Development |
| title_fullStr | Reinforcement Learning-Based Autonomous Soccer Agents: A Study in Multi-Agent Coordination and Strategy Development |
| title_full_unstemmed | Reinforcement Learning-Based Autonomous Soccer Agents: A Study in Multi-Agent Coordination and Strategy Development |
| title_short | Reinforcement Learning-Based Autonomous Soccer Agents: A Study in Multi-Agent Coordination and Strategy Development |
| title_sort | reinforcement learning based autonomous soccer agents a study in multi agent coordination and strategy development |
| topic | q-learning reward reinforcement learning occer agents |
| url | https://journal.ubpkarawang.ac.id/index.php/bit-cs/article/view/7270 |
| work_keys_str_mv | AT biplovpaneru reinforcementlearningbasedautonomoussocceragentsastudyinmultiagentcoordinationandstrategydevelopment AT bishwashpaneru reinforcementlearningbasedautonomoussocceragentsastudyinmultiagentcoordinationandstrategydevelopment AT ramharipoudyal reinforcementlearningbasedautonomoussocceragentsastudyinmultiagentcoordinationandstrategydevelopment AT khempoudyal reinforcementlearningbasedautonomoussocceragentsastudyinmultiagentcoordinationandstrategydevelopment |