arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.10412cs.LGcs.MAstat.ML
收藏

基于图的策略学习实现开放式Ad Hoc团队

Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning

University of Edinburgh(爱丁堡大学);University of Amsterdam(阿姆斯特丹大学)

Arrasy Rahman, Niklas Höpner, Filippos Christianos, Stefano V. Albrecht

摘要:

特设团队合作是设计一个自主智能体的挑战性问题,它可以快速适应与队友合作,而无需事先的协调机制,包括联合训练。在此领域的先前工作集中在封闭的团队中,其中代理的数量是固定的。在这项工作中,我们考虑开放的团队,允许代理人与不同的固定政策,进入和离开环境,而无需事先通知。我们的解决方案建立在图神经网络学习代理模型和联合行动的价值模型在不同的团队组成。我们贡献了一种新的行动价值计算,集成了代理模型和联合行动价值模型,以产生行动价值估计。我们的经验表明,我们的方法成功地模拟了其他代理人对学习者的影响,导致政策,强大地适应动态的团队组成,并显着优于几种替代方法。

英文摘要:

Ad hoc teamwork is the challenging problem of designing an autonomous agent which can adapt quickly to collaborate with teammates without prior coordination mechanisms, including joint training. Prior work in this area has focused on closed teams in which the number of agents is fixed. In this work, we consider open teams by allowing agents with different fixed policies to enter and leave the environment without prior notification. Our solution builds on graph neural networks to learn agent models and joint-action value models under varying team compositions. We contribute a novel action-value computation that integrates the agent model and joint-action value model to produce action-value estimates. We empirically demonstrate that our approach successfully models the effects other agents have on the learner, leading to policies that robustly adapt to dynamic team compositions and significantly outperform several alternative methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑