In this paper a new heuristic optimization algorithm has been introduced based on the performance of the major football leagues within each season in EU countries. The algorithm starts with an initial population including three different groups of teams: the wealthiest (strongest), the regular, the poorest (weakest). Each individual of population constitute a football team while each player is an indication of a player in a post. The optimization can hopefully occurs when the competition among the teams in all the leagues is imitated as the strongest teams usually purchase the best players of the regular teams and in turn, regular teams purchase the best players of the weakest who should always discover young players instead of buying professionals. It has been shown that the algorithm can hopefully converge to an acceptable solution solving various benchmarks. Key words: Heuristic Algorithms
CYRUS Soccer Simulation 2D Team Description Paper 2022
Dalhousie University(达尔豪斯大学);Amirkabir University of Technology(阿米尔卡比尔理工大学);Qom University of Technology(库姆理工大学);Shiraz University(设拉子大学);Polish Academy of Sciences(波兰科学院);Memorial University of Newfoundland(纽芬兰纪念大学)
Observation Denoising in CYRUS Soccer Simulation 2D Team For RoboCup 2023
Memorial University of Newfoundland(纽芬兰纪念大学);Dalhousie University(达尔豪斯大学);Amirkabir University of Technology(阿米尔卡比尔理工大学);Polish Academy of Sciences(波兰科学院)
Improving Dribbling, Passing, and Marking Actions in Soccer Simulation 2D Games Using Machine Learning
Institute for Big Data Analytics, Dalhousie University(达尔豪斯大学大数据分析研究所);Qom University of Technology(库姆科技大学);Shiraz University(设拉子大学);Amirkabir University of Technology(阿米尔卡比尔理工大学);Institute for Computer Science, Polish Academy of Sciences(波兰科学院计算机科学研究所);Memorial University of Newfoundland(纽芬兰纪念大学)
本文介绍了 RoboCup 2021 2D 足球仿真冠军 CYRUS 的三大核心功能:多动作盘带、传球预测和盯人决策,分别提升了盘带成功率、团队协作和防守策略。
An analysis of Reinforcement Learning applied to Coach task in IEEE Very Small Size Soccer
Universidade Federal de Pernambuco(伯南布哥联邦大学)
IEEE Very Small Size Soccer(VSSS)是一项机器人足球比赛,由两队三个小型机器人组成。传统上,一个确定性的教练代理将选择最合适的策略和形成每个对手的策略。因此,教练的角色对比赛至关重要。在这个意义上,本文提出了一种基于强化学习(RL)的辅导任务的端到端的方法。所提出的系统在模拟比赛期间处理信息,以学习根据对手和比赛条件选择当前阵型的最佳策略。我们在模拟环境中针对三支不同的球队(平衡,进攻和严重进攻)训练了两种RL策略。我们的成绩是与VSSS联赛的顶级球队之一进行评估的,在取得约2.0的赢/输比后,我们的成绩很有希望。