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 2101.03238cs.MAcs.LGcs.PL
收藏

用于多智能体通信的神经符号Transformers

Neurosymbolic Transformers for Multi-Agent Communication

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);University of Pennsylvania(宾夕法尼亚大学)

Jeevana Priya Inala, Yichen Yang, James Paulos, Yewen Pu, Osbert Bastani, Vijay Kumar, Martin Rinard, Armando Solar-Lezama

摘要:

我们研究的问题,推断通信结构,可以解决合作的多智能体规划问题,同时最大限度地减少通信量。我们将通信量量化为通信图的最大程度;此度量捕获代理具有有限带宽的设置。由于决策空间和目标的组合性质,最小化通信是具有挑战性的;例如,我们不能通过使用梯度下降训练神经网络来解决这个问题。我们提出了一种新的算法,综合了一个控制策略,结合了一个程序化的通信策略,用于生成的通信图与一个Transformer策略网络用于选择行动。我们的算法首先训练Transformer策略,该策略隐式地生成“软”通信图;然后,它合成“硬化”该图的编程通信策略,形成神经符号Transformer。我们的实验展示了我们的方法如何合成生成低度通信图的策略,同时保持接近最佳的性能。

英文摘要:

We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication. We quantify the amount of communication as the maximum degree of the communication graph; this metric captures settings where agents have limited bandwidth. Minimizing communication is challenging due to the combinatorial nature of both the decision space and the objective; for instance, we cannot solve this problem by training neural networks using gradient descent. We propose a novel algorithm that synthesizes a control policy that combines a programmatic communication policy used to generate the communication graph with a transformer policy network used to choose actions. Our algorithm first trains the transformer policy, which implicitly generates a "soft" communication graph; then, it synthesizes a programmatic communication policy that "hardens" this graph, forming a neurosymbolic transformer. Our experiments demonstrate how our approach can synthesize policies that generate low-degree communication graphs while maintaining near-optimal performance.

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。

↑