In real-world multi-agent systems, agents with different capabilities may join or leave without altering the team's overarching goals. Coordinating teams with such dynamic composition is challenging: the optimal team strategy varies with the composition. We propose COPA, a coach-player framework to tackle this problem. We assume the coach has a global view of the environment and coordinates the players, who only have partial views, by distributing individual strategies. Specifically, we 1) adopt the attention mechanism for both the coach and the players; 2) propose a variational objective to regularize learning; and 3) design an adaptive communication method to let the coach decide when to communicate with the players. We validate our methods on a resource collection task, a rescue game, and the StarCraft micromanagement tasks. We demonstrate zero-shot generalization to new team compositions. Our method achieves comparable or better performance than the setting where all players have a full view of the environment. Moreover, we see that the performance remains high even when the coach communicates as little as 13% of the time using the adaptive communication strategy.
Towards an AI Coach to Infer Team Mental Model Alignment in Healthcare
Rice University(莱斯大学);Harvard Medical School(哈佛医学院);U.S. Dept. of Veterans Affairs(美国退伍军人事务部);Massachusetts Institute of Technology(麻省理工学院);Brigham and Women’s Hospital(布莱根妇女医院)
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。
Department of Computer Engineering(计算机工程系);Arçelik Research Center for Creative Industries(Arçelik创意产业研究中心);Department of Electrical and Electronics Engineering(电气与电子工程系);Department of Psychology(心理学系);Koç University(科奇大学)
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)