相关论文: Cooperative AI via Decentralized Commitment Device…

With the advancements of artificial intelligence (AI), we're seeing more scenarios that require AI to work closely with other agents, whose goals and strategies might not be known beforehand. However, existing approaches for training…

There are many AI tasks involving multiple interacting agents where agents should learn to cooperate and collaborate to effectively perform the task. Here we develop and evaluate various multi-agent protocols to train agents to collaborate…

For AI technology to fulfill its full promises, we must have effective means to ensure Responsible AI behavior and curtail potential irresponsible use, e.g., in areas of privacy protection, human autonomy, robustness, and prevention of…

Machine learning has recently enabled large advances in artificial intelligence, but these results can be highly centralized. The large datasets required are generally proprietary; predictions are often sold on a per-query basis; and…

Multi-robot cooperative control has gained extensive research interest due to its wide applications in civil, security, and military domains. This paper proposes a cooperative control algorithm for multi-robot systems with general linear…

Integrating rule-based policies into reinforcement learning promises to improve data efficiency and generalization in cooperative pursuit problems. However, most implementations do not properly distinguish the influence of neighboring…

This paper presents a first empirical study of agentic AI as autonomous decision-makers in decentralized governance. Using more than 3K proposals from major protocols, we build an agentic AI voter that interprets proposal contexts,…

Decentralized optimization has become a standard paradigm for solving large-scale decision-making problems and training large machine learning models without centralizing data. However, this paradigm introduces new privacy and security…

In decentralized cooperative multi-agent reinforcement learning, agents can aggregate information from one another to learn policies that maximize a team-average objective function. Despite the willingness to cooperate with others, the…

Cooperative control is crucial for the effective operation of dynamical multi-agent systems. Especially for distributed control schemes, it is essential to exchange data between the agents. This becomes a privacy threat if the data is…

We report two decentralized multi-agent cooperative localization algorithms in which, to reduce the communication cost, inter-agent state estimate correlations are not maintained but accounted for implicitly. In our first algorithm, to…

Monitoring human activity in indoor environments is important for applications such as facility management, safety assessment, and space utilization analysis. While mobile robot teams offer the potential to actively improve observation…

Decentralized optimization enables multiple devices to learn a global machine learning model while each individual device only has access to its local dataset. By avoiding the need for training data to leave individual users' devices, it…

Collaborative AI systems (CAISs) aim at working together with humans in a shared space to achieve a common goal. This critical setting yields hazardous circumstances that could harm human beings. Thus, building such systems with strong…

The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial…

Network connectivity plays an important role in the information exchange between different agents in the multi-level networks. In this paper, we establish a game-theoretic framework to capture the uncoordinated nature of the decision-making…

Cooperative decentralized learning relies on direct information exchange between communicating agents, each with access to locally available datasets. The goal is to agree on model parameters that are optimal over all data. However, sharing…

Multi-robot decision-making is the process where multiple robots coordinate actions. In this paper, we aim for efficient and effective multi-robot decision-making despite the robots' limited on-board resources and the often…

AI systems are fallible, and humans can make mistakes in deciding whether to trust AI over their own judgment. Thus, improving human-AI collaboration requires understanding when, why, and how humans decide to rely on AI. We study two…

AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential…