Cooperative communication plays a central role in theories of human cognition, language, development, culture, and human-robot interaction. Prior models of cooperative communication are algorithmic in nature and do not shed light on why cooperation may yield effective belief transmission and what limitations may arise due to differences between beliefs of agents. Through a connection to the theory of optimal transport, we establishing a mathematical framework for cooperative communication. We derive prior models as special cases, statistical interpretations of belief transfer plans, and proofs of robustness and instability. Computational simulations support and elaborate our theoretical results, and demonstrate fit to human behavior. The results show that cooperative communication provably enables effective, robust belief transmission which is required to explain feats of human learning and improve human-machine interaction.
When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Bandits
Princeton University(普林斯顿大学)
在合作土匪,一个框架,捕捉集体顺序决策的基本特征,代理可以最大限度地减少群体遗憾,从而提高性能,通过利用共享信息。然而,共享信息可能是昂贵的,这促使开发政策,最大限度地减少群体遗憾,同时也减少了代理人传达的消息数量。当代理在\textit{every time step}上与它们的邻居共享信息时,现有的合作式强盗算法获得最佳性能,即,充分沟通。这需要$Θ(T)$数量的消息,其中$T$是决策过程的时间范围。我们提出了\textit{ComEx},一种新的具有成本效益的通信协议,在该协议中,该组实现了相同的顺序的性能作为充分的通信,而通信只有$O(\log T)$数量的消息。我们的关键步骤是开发一种方法来识别并仅传达对实现最佳性能至关重要的信息。此外,我们提出了新的算法,几个基准合作的强盗框架,并表明,我们的算法获得\textit{state-of-the-art}性能,同时始终招致一个显着较小的通信成本比现有的算法。
Communication-efficient Distributed Cooperative Learning with Compressed Beliefs
Department of Electrical and Computer Engineering, Rice University(莱斯大学电气与计算机工程系);Rice University(莱斯大学);Houston, TX, USA(美国得克萨斯州休斯敦(此处地址信息不满足机构提取要求,仅保留有效机构部分))
From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights
University of Pittsburgh(匹兹堡大学)
对话者的合作性是对话语用学研究的核心。仅假设合作主体的对话模型无法解释战略对话的动态。因此,我们调查的能力,以确定非合作的对话者,同时完成一个并发的视觉对话任务的代理。在这个新的设置,我们研究的沟通策略,以实现这一多任务目标的最优性。我们运用学习理论的工具,建立了一个识别非合作对话者的理论模型,并应用该理论分析了不同的交际策略。我们还介绍了一个语料库的非合作对话的图像在GuessWhat?!De Vries et al.(2017)提出的数据集。我们使用强化学习在这种情况下实现多种沟通策略,并发现实证结果验证了我们的理论。
Semantic-Forward Relaying: A Novel Framework Towards 6G Cooperative Communications
Northwestern Polytechnical University(西北工业大学);University of Houston(休斯顿大学);Kyung Hee University(庆熙大学);IMT-Atlantique(IMT-大西洋);Japan Advanced Institute of Science Technology(日本先端科学技术大学院大学);University of Oulu(奥卢大学)