This research note is organized with respect to a novel approach to solving problems related to the spread of fake news and effective fact-checking. Focusing on the least-cost routing problem, the discussion is organized with respect to the use of Metzler functions and Metzler matrices to model the dynamics of information propagation among news providers. With this approach, we designed a strategy to minimize the spread of fake news, which is detrimental to informational health, while at the same time maximizing the spread of credible information. In particular, through the punitive dominance problem and the maximum compensation problem, we developed and examined a path to reassess the incentives of news providers to act and to analyze their impact on the equilibrium of the information market. By applying the concept of entanglement to the context of information propagation, we shed light on the complexity of interactions among news providers and contribute to the formulation of more effective information management strategies. This study provides new theoretical and practical insights into issues related to fake news and fact-checking, and will be examined against improving informational health and public digital health.This paper is partially an attempt to utilize "Generative AI" and was written with educational intent. There are currently no plans for it to become a peer-reviewed paper.

In this context, the proliferation of fake news and its impact on society has become a matter of serious concern, and it is critical to understand the mechanisms involved. In this study, we specifically explore how the proliferation of fake news is affected by the strategic behavior and interaction dynamics of individuals. In a scenario where a single werewolf is present, we show that certain agents can have a significant impact on group dynamics by manipulating the flow of information. This result suggests a role for "opinion leaders" or "influencers" in the spread of fake news, and the detection of these agents and the mitigation of their influence may be key to understanding and controlling the dynamics of information dissemination. We have developed models of interactions between individuals and the propagation of information using the framework of incomplete information games and unfolding Figure 1: Network Graph with a Single Werewolf games. In particular, we used the concepts of cocktail party effect and repetition dilemma to analyze how the complexity many other agents an agent interacts with, and the repetition of the decisions agents face and their position in the dilemma represents the balance between an agent's incentives social network affect the spread of fake news and the gains to act cooperatively and non-cooperatively. of individual agents.

Generally, the calculation and memory space required for multi-agent path finding (MAPF) grows exponentially as the number of agents increases. This often results in some MAPF instances being unsolvable under limited computational resources and memory space, thereby limiting the application of MAPF in complex scenarios. Hence, we propose a decomposition approach for MAPF instances, which breaks down instances involving a large number of agents into multiple isolated subproblems involving fewer agents. Moreover, we present a framework to enable general MAPF algorithms to solve each subproblem independently and merge their solutions into one conflict-free final solution, without compromising on solvability. Unlike existing works that propose isolated methods aimed at reducing the time cost of MAPF, our method is applicable to all MAPF methods. In our results, we apply decomposition to multiple state-of-the-art MAPF methods using a classic MAPF benchmark (https://movingai.com/benchmarks/mapf.html). The decomposition of MAPF instances is completed on average within 1s, and its application to seven MAPF methods reduces the memory usage and time cost significantly, particularly for serial methods. To facilitate further research within the community, we have made the source code of the proposed algorithm publicly available (https://github.com/JoeYao-bit/LayeredMAPF).

The sim-to-real gap poses a significant challenge in RL-based multi-agent exploration due to scene quantization and action discretization. Existing platforms suffer from the inefficiency in sampling and the lack of diversity in Multi-Agent Reinforcement Learning (MARL) algorithms across different scenarios, restraining their widespread applications. To fill these gaps, we propose MAexp, a generic platform for multi-agent exploration that integrates a broad range of state-of-the-art MARL algorithms and representative scenarios. Moreover, we employ point clouds to represent our exploration scenarios, leading to high-fidelity environment mapping and a sampling speed approximately 40 times faster than existing platforms. Furthermore, equipped with an attention-based Multi-Agent Target Generator and a Single-Agent Motion Planner, MAexp can work with arbitrary numbers of agents and accommodate various types of robots. Extensive experiments are conducted to establish the first benchmark featuring several high-performance MARL algorithms across typical scenarios for robots with continuous actions, which highlights the distinct strengths of each algorithm in different scenarios.

Recent advances in large language models (LLM) have enabled richer social simulations, allowing for the study of various social phenomena. However, most recent work has used a more omniscient perspective on these simulations (e.g., single LLM to generate all interlocutors), which is fundamentally at odds with the non-omniscient, information asymmetric interactions that involve humans and AI agents in the real world. To examine these differences, we develop an evaluation framework to simulate social interactions with LLMs in various settings (omniscient, non-omniscient). Our experiments show that LLMs perform better in unrealistic, omniscient simulation settings but struggle in ones that more accurately reflect real-world conditions with information asymmetry. Our findings indicate that addressing information asymmetry remains a fundamental challenge for LLM-based agents.

We present the first study on provably efficient randomized exploration in cooperative multi-agent reinforcement learning (MARL). We propose a unified algorithm framework for randomized exploration in parallel Markov Decision Processes (MDPs), and two Thompson Sampling (TS)-type algorithms, CoopTS-PHE and CoopTS-LMC, incorporating the perturbed-history exploration (PHE) strategy and the Langevin Monte Carlo exploration (LMC) strategy respectively, which are flexible in design and easy to implement in practice. For a special class of parallel MDPs where the transition is (approximately) linear, we theoretically prove that both CoopTS-PHE and CoopTS-LMC achieve a $\widetilde{\mathcal{O}}(d^{3/2}H^2\sqrt{MK})$ regret bound with communication complexity $\widetilde{\mathcal{O}}(dHM^2)$, where $d$ is the feature dimension, $H$ is the horizon length, $M$ is the number of agents, and $K$ is the number of episodes. This is the first theoretical result for randomized exploration in cooperative MARL. We evaluate our proposed method on multiple parallel RL environments, including a deep exploration problem (\textit{i.e.,} $N$-chain), a video game, and a real-world problem in energy systems. Our experimental results support that our framework can achieve better performance, even under conditions of misspecified transition models. Additionally, we establish a connection between our unified framework and the practical application of federated learning.

Current approaches to learning cooperative behaviors in multi-agent settings assume relatively restrictive settings. In standard fully cooperative multi-agent reinforcement learning, the learning algorithm controls \textit{all} agents in the scenario, while in ad hoc teamwork, the learning algorithm usually assumes control over only a $\textit{single}$ agent in the scenario. However, many cooperative settings in the real world are much less restrictive. For example, in an autonomous driving scenario, a company might train its cars with the same learning algorithm, yet once on the road, these cars must cooperate with cars from another company. Towards generalizing the class of scenarios that cooperative learning methods can address, we introduce $N$-agent ad hoc teamwork, in which a set of autonomous agents must interact and cooperate with dynamically varying numbers and types of teammates at evaluation time. This paper formalizes the problem, and proposes the $\textit{Policy Optimization with Agent Modelling}$ (POAM) algorithm. POAM is a policy gradient, multi-agent reinforcement learning approach to the NAHT problem, that enables adaptation to diverse teammate behaviors by learning representations of teammate behaviors. Empirical evaluation on StarCraft II tasks shows that POAM improves cooperative task returns compared to baseline approaches, and enables out-of-distribution generalization to unseen teammates.

In this paper, we investigate the problem of embodied multi-agent cooperation, where decentralized agents must cooperate given only partial egocentric views of the world. To effectively plan in this setting, in contrast to learning world dynamics in a single-agent scenario, we must simulate world dynamics conditioned on an arbitrary number of agents' actions given only partial egocentric visual observations of the world. To address this issue of partial observability, we first train generative models to estimate the overall world state given partial egocentric observations. To enable accurate simulation of multiple sets of actions on this world state, we then propose to learn a compositional world model for multi-agent cooperation by factorizing the naturally composable joint actions of multiple agents and compositionally generating the video. By leveraging this compositional world model, in combination with Vision Language Models to infer the actions of other agents, we can use a tree search procedure to integrate these modules and facilitate online cooperative planning. To evaluate the efficacy of our methods, we create two challenging embodied multi-agent long-horizon cooperation tasks using the ThreeDWorld simulator and conduct experiments with 2-4 agents. The results show our compositional world model is effective and the framework enables the embodied agents to cooperate efficiently with different agents across various tasks and an arbitrary number of agents, showing the promising future of our proposed framework. More videos can be found at https://vis-www.cs.umass.edu/combo/.

Although Reinforcement Learning (RL) algorithms acquire sequential behavioral patterns through interactions with the environment, their effectiveness in noisy and high-dimensional scenarios typically relies on specific structural priors. In this paper, we propose a novel and general Structural Information principles-based framework for effective Decision-Making, namely SIDM, approached from an information-theoretic perspective. This paper presents a specific unsupervised partitioning method that forms vertex communities in the state and action spaces based on their feature similarities. An aggregation function, which utilizes structural entropy as the vertex weight, is devised within each community to obtain its embedding, thereby facilitating hierarchical state and action abstractions. By extracting abstract elements from historical trajectories, a directed, weighted, homogeneous transition graph is constructed. The minimization of this graph's high-dimensional entropy leads to the generation of an optimal encoding tree. An innovative two-layer skill-based learning mechanism is introduced to compute the common path entropy of each state transition as its identified probability, thereby obviating the requirement for expert knowledge. Moreover, SIDM can be flexibly incorporated into various single-agent and multi-agent RL algorithms, enhancing their performance. Finally, extensive evaluations on challenging benchmarks demonstrate that, compared with SOTA baselines, our framework significantly and consistently improves the policy's quality, stability, and efficiency up to 32.70%, 88.26%, and 64.86%, respectively.

Current trust and reputation models continue to have significant limitations, such as the inability to deal with agents constantly entering or exiting open multi-agent systems (open MAS), as well as continuously changing behaviors. Our study is based on CA, a previously proposed decentralized computational trust model from the trustee's point of view, inspired by synaptic plasticity and the formation of assemblies in the human brain. It is designed to meet the requirements of highly dynamic and open MAS, and its main difference with most conventional trust and reputation models is that the trustor does not select a trustee to delegate a task; instead, the trustee determines whether it is qualified to successfully execute it. We ran a series of simulations to compare CA model to FIRE, a well-established, decentralized trust and reputation model for open MAS under conditions of continuous trustee and trustor population replacement, as well as continuous change of trustees' abilities to perform tasks. The main finding is that FIRE is superior to changes in the trustee population, whereas CA is resilient to the trustor population changes. When the trustees switch performance profiles FIRE clearly outperforms despite the fact that both models' performances are significantly impacted by this environmental change. Findings lead us to conclude that learning to use the appropriate trust model, according to the dynamic conditions in effect could maximize the trustor's benefits.