سامانه همایش‌ها TSTA | ثبت‌نام و ارسال مقاله کنفرانس‌ها و کنگره‌های ملی

صفحه اصلی / سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران

Short-term gains vs. long-term Success: Reward strategy design for reinforcement learning in football

نویسندگان :

Mohammad Pashaei¹ Amirhossein Tayebi² Hadi Amiri³ Ali Fahim⁴

1- Department of Engineering Science, University of Tehran, Tehran, Iran 2- Department of Engineering Science, University of Tehran, Tehran, Iran 3- Department of Engineering Science, University of Tehran, Tehran, Iran 4- Department of Engineering Science, University of Tehran, Tehran, Iran

کلمات کلیدی :

Reinforcement Learning،Multi-agent systems،Soccer Simulation

چکیده :

Reinforcement learning in complex games like soccer relies heavily on how you define your reward function and environment. In this work, we developed a custom 3v3 soccer environment and implemented two RL-based teams with distinct learning trends: one with a fast convergence but limited long-term adaptation, and another with a slower yet more robust learning trajectory. Simulation shows that despite performing better at the start, the short-term agents fall short of the performance of the long-term agents in the long run, and after passing 50% of the episodes, the win rate of long-term agents rises from 30% in the beginning to 50%.