-
mABC: multi-Agent Blockchain-Inspired Collaboration for root cause analysis in micro-services architecture arXiv.cs.MA Pub Date : 2024-04-18 Wei Zhang, Hongcheng Guo, Jian Yang, Yi Zhang, Chaoran Yan, Zhoujin Tian, Hangyuan Ji, Zhoujun Li, Tongliang Li, Tieqiao Zheng, Chao Chen, Yi Liang, Xu Shi, Liangfan Zheng, Bo Zhang
The escalating complexity of micro-services architecture in cloud-native technologies poses significant challenges for maintaining system stability and efficiency. To conduct root cause analysis (RCA) and resolution of alert events, we propose a pioneering framework, multi-Agent Blockchain-inspired Collaboration for root cause analysis in micro-services architecture (mABC), to revolutionize the AI
-
JointPPO: Diving Deeper into the Effectiveness of PPO in Multi-Agent Reinforcement Learning arXiv.cs.MA Pub Date : 2024-04-18 Chenxing Liu, Guizhong Liu
While Centralized Training with Decentralized Execution (CTDE) has become the prevailing paradigm in Multi-Agent Reinforcement Learning (MARL), it may not be suitable for scenarios in which agents can fully communicate and share observations with each other. Fully centralized methods, also know as Centralized Training with Centralized Execution (CTCE) methods, can fully utilize observations of all
-
Large Language Models for Synthetic Participatory Planning of Shared Automated Electric Mobility Systems arXiv.cs.MA Pub Date : 2024-04-18 Jiangbo Yu
Unleashing the synergies of rapidly evolving mobility technologies in a multi-stakeholder landscape presents unique challenges and opportunities for addressing urban transportation problems. This paper introduces a novel synthetic participatory method, critically leveraging large language models (LLMs) to create digital avatars representing diverse stakeholders to plan shared automated electric mobility
-
RAGAR, Your Falsehood RADAR: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models arXiv.cs.MA Pub Date : 2024-04-18 M. Abdul Khaliq, P. Chang, M. Ma, B. Pflugfelder, F. Miletić
The escalating challenge of misinformation, particularly in the context of political discourse, necessitates advanced solutions for fact-checking. We introduce innovative approaches to enhance the reliability and efficiency of multimodal fact-checking through the integration of Large Language Models (LLMs) with Retrieval-augmented Generation (RAG)- based advanced reasoning techniques. This work proposes
-
Circular Distribution of Agents using Convex Layers arXiv.cs.MA Pub Date : 2024-04-17 Gautam Kumar, Ashwini Ratnoo
This paper considers the problem of conflict-free distribution of agents on a circular periphery encompassing all agents. The two key elements of the proposed policy include the construction of a set of convex layers (nested convex polygons) using the initial positions of the agents, and a novel search space region for each of the agents. The search space for an agent on a convex layer is defined as
-
Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs arXiv.cs.MA Pub Date : 2024-04-17 Kang Wang, Zhishu Shen, Zhen Lei, Tiehua Zhang
Traffic signal control systems (TSCSs) are integral to intelligent traffic management, fostering efficient vehicle flow. Traditional approaches often simplify road networks into standard graphs, which results in a failure to consider the dynamic nature of traffic data at neighboring intersections, thereby neglecting higher-order interconnections necessary for real-time control. To address this, we
-
Self-adaptive PSRO: Towards an Automatic Population-based Game Solver arXiv.cs.MA Pub Date : 2024-04-17 Pengdeng Li, Shuxin Li, Chang Yang, Xinrun Wang, Xiao Huang, Hau Chan, Bo An
Policy-Space Response Oracles (PSRO) as a general algorithmic framework has achieved state-of-the-art performance in learning equilibrium policies of two-player zero-sum games. However, the hand-crafted hyperparameter value selection in most of the existing works requires extensive domain knowledge, forming the main barrier to applying PSRO to different games. In this work, we make the first attempt
-
Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning arXiv.cs.MA Pub Date : 2024-04-17 Wei Duan, Jie Lu, Junyu Xuan
Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations, neglecting higher-order relationships. While several approaches attempt to extend cooperation modelling to encompass behaviour similarities within groups, they commonly
-
Concurrency Model of BDI Programming Frameworks: Why Should We Control It? arXiv.cs.MA Pub Date : 2024-04-16 Martina Baiardi, Samuele Burattini, Giovanni Ciatto, Danilo Pianini, Andrea Omicini, Alessandro Ricci
We provide a taxonomy of concurrency models for BDI frameworks, elicited by analysing state-of-the-art technologies, and aimed at helping both BDI designers and developers in making informed decisions. Comparison among BDI technologies w.r.t. concurrency models reveals heterogeneous support, and low customisability.
-
On the external concurrency of current BDI frameworks for MAS arXiv.cs.MA Pub Date : 2024-04-16 Martina Baiardi, Samuele Burattini, Giovanni Ciatto, Danilo Pianini, Alessandro Ricci, Andrea Omicini
The execution of Belief-Desire-Intention (BDI) agents in a Multi-Agent System (MAS) can be practically implemented on top of low-level concurrency mechanisms that impact on efficiency, determinism, and reproducibility. We argue that developers should specify the MAS behaviour independently of the execution model, and choose or configure the concurrency model later on, according to their target domain's
-
A biologically inspired computational trust model for open multi-agent systems which is resilient to trustor population changes arXiv.cs.MA Pub Date : 2024-04-13 Zoi Lygizou, Dimitris Kalles
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
-
COMBO: Compositional World Models for Embodied Multi-Agent Cooperation arXiv.cs.MA Pub Date : 2024-04-16 Hongxin Zhang, Zeyuan Wang, Qiushi Lyu, Zheyuan Zhang, Sunli Chen, Tianmin Shu, Yilun Du, Chuang Gan
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
-
Driver Fatigue Prediction using Randomly Activated Neural Networks for Smart Ridesharing Platforms arXiv.cs.MA Pub Date : 2024-04-16 Sree Pooja Akula, Mukund Telukunta, Venkata Sriram Siddhardh Nadendla
Drivers in ridesharing platforms exhibit cognitive atrophy and fatigue as they accept ride offers along the day, which can have a significant impact on the overall efficiency of the ridesharing platform. In contrast to the current literature which focuses primarily on modeling and learning driver's preferences across different ride offers, this paper proposes a novel Dynamic Discounted Satisficing
-
A Cloud Resources Portfolio Optimization Business Model - From Theory to Practice arXiv.cs.MA Pub Date : 2024-04-16 Valentin Haag, Maximilian Kiessler, Benedikt Pittl, Erich Schikuta
Cloud resources have become increasingly important, with many businesses using cloud solutions to supplement or outright replace their existing IT infrastructure. However, as there is a plethora of providers with varying products, services, and markets, it has become increasingly more challenging to keep track of the best solutions for each application. Cloud service intermediaries aim to alleviate
-
PreGSU-A Generalized Traffic Scene Understanding Model for Autonomous Driving based on Pre-trained Graph Attention Network arXiv.cs.MA Pub Date : 2024-04-16 Yuning Wang, Zhiyuan Liu, Haotian Lin, Junkai Jiang, Shaobing Xu, Jianqiang Wang
Scene understanding, defined as learning, extraction, and representation of interactions among traffic elements, is one of the critical challenges toward high-level autonomous driving (AD). Current scene understanding methods mainly focus on one concrete single task, such as trajectory prediction and risk level evaluation. Although they perform well on specific metrics, the generalization ability is
-
Kernel-based learning with guarantees for multi-agent applications arXiv.cs.MA Pub Date : 2024-04-15 Krzysztof Kowalczyk, Paweł Wachel, Cristian R. Rojas
This paper addresses a kernel-based learning problem for a network of agents locally observing a latent multidimensional, nonlinear phenomenon in a noisy environment. We propose a learning algorithm that requires only mild a priori knowledge about the phenomenon under investigation and delivers a model with corresponding non-asymptotic high probability error bounds. Both non-asymptotic analysis of
-
Correlated Mean Field Imitation Learning arXiv.cs.MA Pub Date : 2024-04-14 Zhiyu Zhao, Ning Yang, Xue Yan, Haifeng Zhang, Jun Wang, Yaodong Yang
We investigate multi-agent imitation learning (IL) within the framework of mean field games (MFGs), considering the presence of time-varying correlated signals. Existing MFG IL algorithms assume demonstrations are sampled from Mean Field Nash Equilibria (MFNE), limiting their adaptability to real-world scenarios. For example, in the traffic network equilibrium influenced by public routing recommendations
-
An Agent-Based Model of Elephant Crop Raid Dynamics in the Periyar-Agasthyamalai Complex, India arXiv.cs.MA Pub Date : 2024-04-13 Purathekandy Anjali, Meera Anna Oommen, Martin Wikelski, Deepak N Subramani
Human-wildlife conflict poses significant challenges to conservation efforts around the world and requires innovative solutions for effective management. We developed an agent-based model to simulate complex interactions between humans and Asian elephants (particularly solitary bull elephants) in the Periyar-Agasthyamalai complex of the Western Ghats in Kerala, India. Incorporating factors such as
-
Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning arXiv.cs.MA Pub Date : 2024-04-15 Linjie Xu, Zichuan Liu, Alexander Dockhorn, Diego Perez-Liebana, Jinyu Wang, Lei Song, Jiang Bian
One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MARL) is more challenging because of its inherent partial observability, non-stationary training, and enormous strategy space. Although much effort has been devoted to developing new methods and enhancing sample efficiency
-
Monitoring Second-Order Hyperproperties arXiv.cs.MA Pub Date : 2024-04-15 Raven Beutner, Bernd Finkbeiner, Hadar Frenkel, Niklas Metzger
Hyperproperties express the relationship between multiple executions of a system. This is needed in many AI-related fields, such as knowledge representation and planning, to capture system properties related to knowledge, information flow, and privacy. In this paper, we study the monitoring of complex hyperproperties at runtime. Previous work in this area has either focused on the simpler problem of
-
Multi-Agent eXperimenter (MAX) arXiv.cs.MA Pub Date : 2024-04-12 Önder Gürcan
We present a novel multi-agent simulator named Multi-Agent eXperimenter (MAX) that is designed to simulate blockchain experiments involving large numbers of agents of different types acting in one or several environments. The architecture of MAX is highly modular, enabling easy addition of new models.
-
Q-ITAGS: Quality-Optimized Spatio-Temporal Heterogeneous Task Allocation with a Time Budget arXiv.cs.MA Pub Date : 2024-04-11 Glen Neville, Jiazhen Liu, Sonia Chernova, Harish Ravichandar
Complex multi-objective missions require the coordination of heterogeneous robots at multiple inter-connected levels, such as coalition formation, scheduling, and motion planning. The associated challenges are exacerbated when solutions to these interconnected problems need to both maximize task performance and respect practical constraints on time and resources. In this work, we formulate a new class
-
WESE: Weak Exploration to Strong Exploitation for LLM Agents arXiv.cs.MA Pub Date : 2024-04-11 Xu Huang, Weiwen Liu, Xiaolong Chen, Xingmei Wang, Defu Lian, Yasheng Wang, Ruiming Tang, Enhong Chen
Recently, large language models (LLMs) have demonstrated remarkable potential as an intelligent agent. However, existing researches mainly focus on enhancing the agent's reasoning or decision-making abilities through well-designed prompt engineering or task-specific fine-tuning, ignoring the procedure of exploration and exploitation. When addressing complex tasks within open-world interactive environments
-
The Power in Communication: Power Regularization of Communication for Autonomy in Cooperative Multi-Agent Reinforcement Learning arXiv.cs.MA Pub Date : 2024-04-09 Nancirose Piazza, Vahid Behzadan, Stefan Sarkadi
Communication plays a vital role for coordination in Multi-Agent Reinforcement Learning (MARL) systems. However, misaligned agents can exploit other agents' trust and delegated power to the communication medium. In this paper, we propose power regularization as a method to limit the adverse effects of communication by misaligned agents, specifically communication which impairs the performance of cooperative
-
NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata arXiv.cs.MA Pub Date : 2024-04-09 Ehsan Pajouheshgar, Yitao Xu, Sabine Süsstrunk
Neural Cellular Automata (NCA) is a class of Cellular Automata where the update rule is parameterized by a neural network that can be trained using gradient descent. In this paper, we focus on NCA models used for texture synthesis, where the update rule is inspired by partial differential equations (PDEs) describing reaction-diffusion systems. To train the NCA model, the spatio-termporal domain is
-
Attention-Driven Multi-Agent Reinforcement Learning: Enhancing Decisions with Expertise-Informed Tasks arXiv.cs.MA Pub Date : 2024-04-08 Andre R Kuroswiski, Annie S Wu, Angelo Passaro
In this paper, we introduce an alternative approach to enhancing Multi-Agent Reinforcement Learning (MARL) through the integration of domain knowledge and attention-based policy mechanisms. Our methodology focuses on the incorporation of domain-specific expertise into the learning process, which simplifies the development of collaborative behaviors. This approach aims to reduce the complexity and learning
-
Automatic Gradient Estimation for Calibrating Crowd Models with Discrete Decision Making arXiv.cs.MA Pub Date : 2024-04-06 Philipp Andelfinger, Justin N. Kreikemeyer
Recently proposed gradient estimators enable gradient descent over stochastic programs with discrete jumps in the response surface, which are not covered by automatic differentiation (AD) alone. Although these estimators' capability to guide a swift local search has been shown for certain problems, their applicability to models relevant to real-world applications remains largely unexplored. As the
-
ROMA-iQSS: An Objective Alignment Approach via State-Based Value Learning and ROund-Robin Multi-Agent Scheduling arXiv.cs.MA Pub Date : 2024-04-05 Chi-Hui Lin, Joewie J. Koh, Alessandro Roncone, Lijun Chen
Effective multi-agent collaboration is imperative for solving complex, distributed problems. In this context, two key challenges must be addressed: first, autonomously identifying optimal objectives for collective outcomes; second, aligning these objectives among agents. Traditional frameworks, often reliant on centralized learning, struggle with scalability and efficiency in large multi-agent systems
-
No Panacea in Planning: Algorithm Selection for Suboptimal Multi-Agent Path Finding arXiv.cs.MA Pub Date : 2024-04-04 Weizhe Chen, Zhihan Wang, Jiaoyang Li, Sven Koenig, Bistra Dilkina
Since more and more algorithms are proposed for multi-agent path finding (MAPF) and each of them has its strengths, choosing the correct one for a specific scenario that fulfills some specified requirements is an important task. Previous research in algorithm selection for MAPF built a standard workflow and showed that machine learning can help. In this paper, we study general solvers for MAPF, which
-
MEDIATE: Mutually Endorsed Distributed Incentive Acknowledgment Token Exchange arXiv.cs.MA Pub Date : 2024-04-04 Philipp Altmann, Katharina Winter, Michael Kölle, Maximilian Zorn, Thomy Phan, Claudia Linnhoff-Popien
Recent advances in multi-agent systems (MAS) have shown that incorporating peer incentivization (PI) mechanisms vastly improves cooperation. Especially in social dilemmas, communication between the agents helps to overcome sub-optimal Nash equilibria. However, incentivization tokens need to be carefully selected. Furthermore, real-world applications might yield increased privacy requirements and limited
-
MARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search arXiv.cs.MA Pub Date : 2024-04-03 Weizhe Chen, Sven Koenig, Bistra Dilkina
Cooperative multi-agent reinforcement learning (MARL) has been an increasingly important research topic in the last half-decade because of its great potential for real-world applications. Because of the curse of dimensionality, the popular "centralized training decentralized execution" framework requires a long time in training, yet still cannot converge efficiently. In this paper, we propose a general
-
Laser Learning Environment: A new environment for coordination-critical multi-agent tasks arXiv.cs.MA Pub Date : 2024-04-04 Yannick Molinghen, Raphaël Avalos, Mark Van Achter, Ann Nowé, Tom Lenaerts
We introduce the Laser Learning Environment (LLE), a collaborative multi-agent reinforcement learning environment in which coordination is central. In LLE, agents depend on each other to make progress (interdependence), must jointly take specific sequences of actions to succeed (perfect coordination), and accomplishing those joint actions does not yield any intermediate reward (zero-incentive dynamics)
-
Best Response Shaping arXiv.cs.MA Pub Date : 2024-04-05 Milad Aghajohari, Tim Cooijmans, Juan Agustin Duque, Shunichi Akatsuka, Aaron Courville
We investigate the challenge of multi-agent deep reinforcement learning in partially competitive environments, where traditional methods struggle to foster reciprocity-based cooperation. LOLA and POLA agents learn reciprocity-based cooperative policies by differentiation through a few look-ahead optimization steps of their opponent. However, there is a key limitation in these techniques. Because they
-
EnergAIze: Multi Agent Deep Deterministic Policy Gradient for Vehicle to Grid Energy Management arXiv.cs.MA Pub Date : 2024-04-02 Tiago Fonseca, Luis Ferreira, Bernardo Cabral, Ricardo Severino, Isabel Praca
This paper investigates the increasing roles of Renewable Energy Sources (RES) and Electric Vehicles (EVs). While indicating a new era of sustainable energy, these also introduce complex challenges, including the need to balance supply and demand and smooth peak consumptions amidst rising EV adoption rates. Addressing these challenges requires innovative solutions such as Demand Response (DR), energy
-
Distributed Autonomous Swarm Formation for Dynamic Network Bridging arXiv.cs.MA Pub Date : 2024-04-02 Raffaele Galliera, Thies Möhlenhof, Alessandro Amato, Daniel Duran, Kristen Brent Venable, Niranjan Suri
Effective operation and seamless cooperation of robotic systems are a fundamental component of next-generation technologies and applications. In contexts such as disaster response, swarm operations require coordinated behavior and mobility control to be handled in a distributed manner, with the quality of the agents' actions heavily relying on the communication between them and the underlying network
-
Multi-Agent Reinforcement Learning with Control-Theoretic Safety Guarantees for Dynamic Network Bridging arXiv.cs.MA Pub Date : 2024-04-02 Raffaele Galliera, Konstantinos Mitsopoulos, Niranjan Suri, Raffaele Romagnoli
Addressing complex cooperative tasks in safety-critical environments poses significant challenges for Multi-Agent Systems, especially under conditions of partial observability. This work introduces a hybrid approach that integrates Multi-Agent Reinforcement Learning with control-theoretic methods to ensure safe and efficient distributed strategies. Our contributions include a novel setpoint update
-
Emergence of Chemotactic Strategies with Multi-Agent Reinforcement Learning arXiv.cs.MA Pub Date : 2024-04-02 Samuel Tovey, Christoph Lohrmann, Christian Holm
Reinforcement learning (RL) is a flexible and efficient method for programming micro-robots in complex environments. Here we investigate whether reinforcement learning can provide insights into biological systems when trained to perform chemotaxis. Namely, whether we can learn about how intelligent agents process given information in order to swim towards a target. We run simulations covering a range
-
Safe Interval RRT* for Scalable Multi-Robot Path Planning in Continuous Space arXiv.cs.MA Pub Date : 2024-04-02 Joonyeol Sim, Joonkyung Kim, Changjoo Nam
In this paper, we consider the problem of Multi-Robot Path Planning (MRPP) in continuous space to find conflict-free paths. The difficulty of the problem arises from two primary factors. First, the involvement of multiple robots leads to combinatorial decision-making, which escalates the search space exponentially. Second, the continuous space presents potentially infinite states and actions. For this
-
GOV-REK: Governed Reward Engineering Kernels for Designing Robust Multi-Agent Reinforcement Learning Systems arXiv.cs.MA Pub Date : 2024-04-01 Ashish Rana, Michael Oesterle, Jannik Brinkmann
For multi-agent reinforcement learning systems (MARLS), the problem formulation generally involves investing massive reward engineering effort specific to a given problem. However, this effort often cannot be translated to other problems; worse, it gets wasted when system dynamics change drastically. This problem is further exacerbated in sparse reward scenarios, where a meaningful heuristic can assist
-
A CRISP-DM-based Methodology for Assessing Agent-based Simulation Models using Process Mining arXiv.cs.MA Pub Date : 2024-04-01 Rob H. Bemthuis, Ruben R. Govers, Amin Asadi
Agent-based simulation (ABS) models are potent tools for analyzing complex systems. However, understanding and validating ABS models can be a significant challenge. To address this challenge, cutting-edge data-driven techniques offer sophisticated capabilities for analyzing the outcomes of ABS models. One such technique is process mining, which encompasses a range of methods for discovering, monitoring
-
Can LLMs get help from other LLMs without revealing private information? arXiv.cs.MA Pub Date : 2024-04-01 Florian Hartmann, Duc-Hieu Tran, Peter Kairouz, Victor Cărbune, Blaise Aguera y Arcas
Cascades are a common type of machine learning systems in which a large, remote model can be queried if a local model is not able to accurately label a user's data by itself. Serving stacks for large language models (LLMs) increasingly use cascades due to their ability to preserve task performance while dramatically reducing inference costs. However, applying cascade systems in situations where the
-
A Stackelberg Regret Minimizing Framework for Online Learning in Newsvendor Pricing Games arXiv.cs.MA Pub Date : 2024-03-30 Larkin Liu, Yuming Rong
We introduce the application of online learning in a Stackelberg game pertaining to a system with two learning agents in a dyadic exchange network, consisting of a supplier and retailer, specifically where the parameters of the demand function are unknown. In this game, the supplier is the first-moving leader, and must determine the optimal wholesale price of the product. Subsequently, the retailer
-
Existence and Verification of Nash Equilibria in Non-Cooperative Contribution Games with Resource Contention arXiv.cs.MA Pub Date : 2024-03-29 Nicolas Troquard
In resource contribution games, a class of non-cooperative games, the players want to obtain a bundle of resources and are endowed with bags of bundles of resources that they can make available into a common for all to enjoy. Available resources can then be used towards their private goals. A player is potentially satisfied with a profile of contributed resources when his bundle could be extracted
-
Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning arXiv.cs.MA Pub Date : 2024-03-28 Wei Duan, Jie Lu, Junyu Xuan
Effective agent coordination is crucial in cooperative Multi-Agent Reinforcement Learning (MARL). While agent cooperation can be represented by graph structures, prevailing graph learning methods in MARL are limited. They rely solely on one-step observations, neglecting crucial historical experiences, leading to deficient graphs that foster redundant or detrimental information exchanges. Additionally
-
Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning arXiv.cs.MA Pub Date : 2024-03-27 Soumyendu Sarkar, Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha, Avisek Naug, Sahand Ghorbanpour
We present a generic Reinforcement Learning (RL) framework optimized for crafting adversarial attacks on different model types spanning from ECG signal analysis (1D), image classification (2D), and video classification (3D). The framework focuses on identifying sensitive regions and inducing misclassifications with minimal distortions and various distortion types. The novel RL method outperforms state-of-the-art
-
Safety Verification of Wait-Only Non-Blocking Broadcast Protocols arXiv.cs.MA Pub Date : 2024-03-27 Lucie Guillou, Arnaud Sangnier, Nathalie Sznajder
We study networks of processes that all execute the same finite protocol and communicate synchronously in two different ways: a process can broadcast one message to all other processes or send it to at most one other process. In both cases, if no process can receive the message, it will still be sent. We establish a precise complexity class for two coverability problems with a parameterised number
-
Towards a Formalisation of Value-based Actions and Consequentialist Ethics arXiv.cs.MA Pub Date : 2024-03-25 Adam Wyner, Tomasz Zurek, DOrota Stachura-Zurek
Agents act to bring about a state of the world that is more compatible with their personal or institutional values. To formalise this intuition, the paper proposes an action framework based on the STRIPS formalisation. Technically, the contribution expresses actions in terms of Value-based Formal Reasoning (VFR), which provides a set of propositions derived from an Agent's value profile and the Agent's
-
Norm Violation Detection in Multi-Agent Systems using Large Language Models: A Pilot Study arXiv.cs.MA Pub Date : 2024-03-25 Shawn He, Surangika Ranathunga, Stephen Cranefield, Bastin Tony Roy Savarimuthu
Norms are an important component of the social fabric of society by prescribing expected behaviour. In Multi-Agent Systems (MAS), agents interacting within a society are equipped to possess social capabilities such as reasoning about norms and trust. Norms have long been of interest within the Normative Multi-Agent Systems community with researchers studying topics such as norm emergence, norm violation
-
Social Deliberation vs. Social Contracts in Self-Governing Voluntary Organisations arXiv.cs.MA Pub Date : 2024-03-24 Matthew Scott, Asimina Mertzani, Ciske Smit, Stefan Sarkadi, Jeremy Pitt
Self-organising multi-agent systems regulate their components' behaviour voluntarily, according to a set of socially-constructed, mutually-agreed, and mutable social arrangements. In some systems, these arrangements may be applied with a frequency, at a scale and within implicit cost constraints such that performance becomes a pressing issue. This paper introduces the \textit{Megabike Scenario}, which
-
Team Coordination on Graphs: Problem, Analysis, and Algorithms arXiv.cs.MA Pub Date : 2024-03-23 Manshi Limbu, Yanlin Zhou, Gregory Stein, Xuan Wang, Daigo Shishika, Xuesu Xiao
Team Coordination on Graphs with Risky Edges (TCGRE) is a recently emerged problem, in which a robot team collectively reduces graph traversal cost through support from one robot to another when the latter traverses a risky edge. Resembling the traditional Multi-Agent Path Finding (MAPF) problem, both classical and learning-based methods have been proposed to solve TCGRE, however, they lacked either
-
Compressed Federated Reinforcement Learning with a Generative Model arXiv.cs.MA Pub Date : 2024-03-26 Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon
Reinforcement learning has recently gained unprecedented popularity, yet it still grapples with sample inefficiency. Addressing this challenge, federated reinforcement learning (FedRL) has emerged, wherein agents collaboratively learn a single policy by aggregating local estimations. However, this aggregation step incurs significant communication costs. In this paper, we propose CompFedRL, a communication-efficient
-
An Agent-Centric Perspective on Norm Enforcement and Sanctions arXiv.cs.MA Pub Date : 2024-03-22 Elena Yan, Luis G. Nardin, Jomi F. Hübner, Olivier Boissier
In increasingly autonomous and highly distributed multi-agent systems, centralized coordination becomes impractical and raises the need for governance and enforcement mechanisms from an agent-centric perspective. In our conceptual view, sanctioning norm enforcement is part of this agent-centric approach and they aim at promoting norm compliance while preserving agents' autonomy. The few works dealing
-
Collaborative AI Teaming in Unknown Environments via Active Goal Deduction arXiv.cs.MA Pub Date : 2024-03-22 Zuyuan Zhang, Hanhan Zhou, Mahdi Imani, Taeyoung Lee, Tian Lan
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 collaborative agents often require defined and known reward signals and cannot address the problem of teaming with unknown agents that often have latent objectives/rewards
-
CACA Agent: Capability Collaboration based AI Agent arXiv.cs.MA Pub Date : 2024-03-22 Peng Xu, Haoran Wang, Chuang Wang, Xu Liu
As AI Agents based on Large Language Models (LLMs) have shown potential in practical applications across various fields, how to quickly deploy an AI agent and how to conveniently expand the application scenario of AI agents has become a challenge. Previous studies mainly focused on implementing all the reasoning capabilities of AI agents within a single LLM, which often makes the model more complex
-
Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games arXiv.cs.MA Pub Date : 2024-03-25 Muhammad Aneeq uz Zaman, Shubham Aggarwal, Melih Bastopcu, Tamer Başar
In this paper, we investigate the impact of introducing relative entropy regularization on the Nash Equilibria (NE) of General-Sum $N$-agent games, revealing the fact that the NE of such games conform to linear Gaussian policies. Moreover, it delineates sufficient conditions, contingent upon the adequacy of entropy regularization, for the uniqueness of the NE within the game. As Policy Optimization
-
Motion Prediction of Multi-agent systems with Multi-view clustering arXiv.cs.MA Pub Date : 2024-03-20 Anegi James, Efstathios Bakolas
This paper presents a method for future motion prediction of multi-agent systems by including group formation information and future intent. Formation of groups depends on a physics-based clustering method that follows the agglomerative hierarchical clustering algorithm. We identify clusters that incorporate the minimum cost-to-go function of a relevant optimal control problem as a metric for clustering
-
The Era of Semantic Decoding arXiv.cs.MA Pub Date : 2024-03-21 Maxime Peyrard, Martin Josifoski, Robert West
Recent work demonstrated great promise in the idea of orchestrating collaborations between LLMs, human input, and various tools to address the inherent limitations of LLMs. We propose a novel perspective called semantic decoding, which frames these collaborative processes as optimization procedures in semantic space. Specifically, we conceptualize LLMs as semantic processors that manipulate meaningful
-
Hyper Strategy Logic arXiv.cs.MA Pub Date : 2024-03-20 Raven Beutner, Bernd Finkbeiner
Strategy logic (SL) is a powerful temporal logic that enables strategic reasoning in multi-agent systems. SL supports explicit (first-order) quantification over strategies and provides a logical framework to express many important properties such as Nash equilibria, dominant strategies, etc. While in SL the same strategy can be used in multiple strategy profiles, each such profile is evaluated w.r
-
Multi-agent Reinforcement Traffic Signal Control based on Interpretable Influence Mechanism and Biased ReLU Approximation arXiv.cs.MA Pub Date : 2024-03-20 Zhiyue Luo, Jun Xu, Fanglin Chen
Traffic signal control is important in intelligent transportation system, of which cooperative control is difficult to realize but yet vital. Many methods model multi-intersection traffic networks as grids and address the problem using multi-agent reinforcement learning (RL). Despite these existing studies, there is an opportunity to further enhance our understanding of the connectivity and globality
-
Optimizing Ride-Pooling Revenue: Pricing Strategies and Driver-Traveller Dynamics arXiv.cs.MA Pub Date : 2024-03-20 Usman Akhtar, Farnoud Ghasemi, Rafal Kucharski
Ride-pooling, to gain momentum, needs to be attractive for all the parties involved. This includes also drivers, who are naturally reluctant to serve pooled rides. This can be controlled by the platform's pricing strategy, which can stimulate drivers to serve pooled rides. Here, we propose an agent-based framework, where drivers serve rides that maximise their utility. We simulate a series of scenarios