Adaptive Agents and Multi-Agent Systems最新文献_第2页

Revenue Maximization Mechanisms for an Uninformed Mediator with Communication Abilities 具有沟通能力的不知情调解人的收益最大化机制

Adaptive Agents and Multi-Agent Systems Pub Date : 2023-08-01 DOI: 10.5555/3545946.3599124

Zhikang Fan, Weiran Shen

{"title":"Revenue Maximization Mechanisms for an Uninformed Mediator with Communication Abilities","authors":"Zhikang Fan, Weiran Shen","doi":"10.5555/3545946.3599124","DOIUrl":"https://doi.org/10.5555/3545946.3599124","url":null,"abstract":"Consider a market where a seller owns an item for sale and a buyer wants to purchase it. Each player has private information, known as their type. It can be costly and difficult for the players to reach an agreement through direct communication. However, with a mediator as a trusted third party, both players can communicate privately with the mediator without worrying about leaking too much or too little information. The mediator can design and commit to a multi-round communication protocol for both players, in which they update their beliefs about the other player's type. The mediator cannot force the players to trade but can influence their behaviors by sending messages to them.\u0000\u0000\u0000\u0000We study the problem of designing revenue-maximizing mechanisms for the mediator. We show that the mediator can, without loss of generality, focus on a set of direct and incentive-compatible mechanisms. We then formulate this problem as a mathematical program and provide an optimal solution in closed form under a regularity condition. Our mechanism is simple and has a threshold structure. We also discuss some interesting properties of the optimal mechanism, such as situations where the mediator may lose money.","PeriodicalId":326727,"journal":{"name":"Adaptive Agents and Multi-Agent Systems","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127636293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deliberation as Evidence Disclosure: A Tale of Two Protocol Types 审议作为证据披露:两种协议类型的故事

Adaptive Agents and Multi-Agent Systems Pub Date : 2023-08-01 DOI: 10.5555/3545946.3599105

Julian Chingoma, Adrian Haret

引用次数: 0

Asynchronous Communication Aware Multi-Agent Task Allocation 异步通信感知多代理任务分配

Adaptive Agents and Multi-Agent Systems Pub Date : 2023-08-01 DOI: 10.5555/3545946.3598927

Ben Rachmut, Sofia Amador Nelke, R. Zivan

引用次数: 0

Strategic Play By Resource-Bounded Agents in Security Games 安全博弈中资源有限主体的策略博弈

Adaptive Agents and Multi-Agent Systems Pub Date : 2023-07-25 DOI: 10.5555/3545946.3598973

Xinming Liu, J. Halpern

{"title":"Strategic Play By Resource-Bounded Agents in Security Games","authors":"Xinming Liu, J. Halpern","doi":"10.5555/3545946.3598973","DOIUrl":"https://doi.org/10.5555/3545946.3598973","url":null,"abstract":"Many studies have shown that humans are\"predictably irrational\": they do not act in a fully rational way, but their deviations from rational behavior are quite systematic. Our goal is to see the extent to which we can explain and justify these deviations as the outcome of rational but resource-bounded agents doing as well as they can, given their limitations. We focus on the well-studied ranger-poacher game, where rangers are trying to protect a number of sites from poaching. We capture the computational limitations by modeling the poacher and the ranger as probabilistic finite automata (PFAs). We show that, with sufficiently large memory, PFAs learn to play the Nash equilibrium (NE) strategies of the game and achieve the NE utility. However, if we restrict the memory, we get more\"human-like\"behaviors, such as probability matching (i.e., visiting sites in proportion to the probability of a rhino being there), and avoiding sites where there was a bad outcome (e.g., the poacher was caught by the ranger), that we also observed in experiments conducted on Amazon Mechanical Turk. Interestingly, we find that adding human-like behaviors such as probability matching and overweighting significant events (like getting caught) actually improves performance, showing that this seemingly irrational behavior can be quite rational.","PeriodicalId":326727,"journal":{"name":"Adaptive Agents and Multi-Agent Systems","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116731312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing Smart, Sustainable Mobility with Game Theory and Multi-Agent Reinforcement Learning 用博弈论和多智能体强化学习增强智能、可持续的交通

Adaptive Agents and Multi-Agent Systems Pub Date : 2023-06-26 DOI: 10.5555/3545946.3599163

Lucia Cipolina-Kun

引用次数: 0

Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization 基于耦合值分解的离线多智能体强化学习

Adaptive Agents and Multi-Agent Systems Pub Date : 2023-06-15 DOI: 10.5555/3545946.3599076

Xiangsen Wang, Xianyuan Zhan

{"title":"Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization","authors":"Xiangsen Wang, Xianyuan Zhan","doi":"10.5555/3545946.3599076","DOIUrl":"https://doi.org/10.5555/3545946.3599076","url":null,"abstract":"Offline reinforcement learning (RL) that learns policies from offline datasets without environment interaction has received considerable attention in recent years. Compared with the rich literature in the single-agent case, offline multi-agent RL is still a relatively underexplored area. Most existing methods directly apply offline RL ingredients in the multi-agent setting without fully leveraging the decomposable problem structure, leading to less satisfactory performance in complex tasks. We present OMAC, a new offline multi-agent RL algorithm with coupled value factorization. OMAC adopts a coupled value factorization scheme that decomposes the global value function into local and shared components, and also maintains the credit assignment consistency between the state-value and Q-value functions. Moreover, OMAC performs in-sample learning on the decomposed local state-value functions, which implicitly conducts max-Q operation at the local level while avoiding distributional shift caused by evaluating out-of-distribution actions. Based on the comprehensive evaluations of the offline multi-agent StarCraft II micro-management tasks, we demonstrate the superior performance of OMAC over the state-of-the-art offline multi-agent RL methods.","PeriodicalId":326727,"journal":{"name":"Adaptive Agents and Multi-Agent Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126891576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learnability with PAC Semantics for Multi-agent Beliefs 多智能体信念PAC语义的可学习性

Adaptive Agents and Multi-Agent Systems Pub Date : 2023-06-08 DOI: 10.5555/3545946.3599016

I. Mocanu, Vaishak Belle, Brendan Juba

{"title":"Learnability with PAC Semantics for Multi-agent Beliefs","authors":"I. Mocanu, Vaishak Belle, Brendan Juba","doi":"10.5555/3545946.3599016","DOIUrl":"https://doi.org/10.5555/3545946.3599016","url":null,"abstract":"\u0000 The tension between deduction and induction is perhaps the most fundamental issue in areas such as philosophy, cognition, and artificial intelligence. In an influential paper, Valiant recognized that the challenge of learning should be integrated with deduction. In particular, he proposed a semantics to capture the quality possessed by the output of probably approximately correct (PAC) learning algorithms when formulated in a logic. Although weaker than classical entailment, it allows for a powerful model-theoretic framework for answering queries. In this paper, we provide a new technical foundation to demonstrate PAC learning with multi-agent epistemic logics. To circumvent the negative results in the literature on the difficulty of robust learning with the PAC semantics, we consider so-called implicit learning where we are able to incorporate observations to the background theory in service of deciding the entailment of an epistemic query. We prove correctness of the learning procedure and discuss results on the sample complexity, that is how many observations we will need to provably assert that the query is entailed given a user-specified error bound. Finally, we investigate under what circumstances this algorithm can be made efficient. On the last point, given that reasoning in epistemic logics especially in multi-agent epistemic logics is PSPACE-complete, it might seem like there is no hope for this problem. We leverage some recent results on the so-called Representation Theorem explored for single-agent and multi-agent epistemic logics with the only knowing operator to reduce modal reasoning to propositional reasoning.","PeriodicalId":326727,"journal":{"name":"Adaptive Agents and Multi-Agent Systems","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128884704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modeling Dynamic Environments with Scene Graph Memory 基于场景图记忆的动态环境建模

Adaptive Agents and Multi-Agent Systems Pub Date : 2023-05-27 DOI: 10.5555/3545946.3599100

Andrey Kurenkov, Michael Lingelbach, Tanmay Agarwal, Chengshu Li, Emily Jin, Ruohan Zhang, Li Fei-Fei, Jiajun Wu, S. Savarese, Roberto Martín-Martín

{"title":"Modeling Dynamic Environments with Scene Graph Memory","authors":"Andrey Kurenkov, Michael Lingelbach, Tanmay Agarwal, Chengshu Li, Emily Jin, Ruohan Zhang, Li Fei-Fei, Jiajun Wu, S. Savarese, Roberto Martín-Martín","doi":"10.5555/3545946.3599100","DOIUrl":"https://doi.org/10.5555/3545946.3599100","url":null,"abstract":"Embodied AI agents that search for objects in large environments such as households often need to make efficient decisions by predicting object locations based on partial information. We pose this as a new type of link prediction problem: link prediction on partially observable dynamic graphs. Our graph is a representation of a scene in which rooms and objects are nodes, and their relationships are encoded in the edges; only parts of the changing graph are known to the agent at each timestep. This partial observability poses a challenge to existing link prediction approaches, which we address. We propose a novel state representation -- Scene Graph Memory (SGM) -- with captures the agent's accumulated set of observations, as well as a neural net architecture called a Node Edge Predictor (NEP) that extracts information from the SGM to search efficiently. We evaluate our method in the Dynamic House Simulator, a new benchmark that creates diverse dynamic graphs following the semantic patterns typically seen at homes, and show that NEP can be trained to predict the locations of objects in a variety of environments with diverse object movement dynamics, outperforming baselines both in terms of new scene adaptability and overall accuracy. The codebase and more can be found at https://www.scenegraphmemory.com.","PeriodicalId":326727,"journal":{"name":"Adaptive Agents and Multi-Agent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130570962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Reward-Machine-Guided, Self-Paced Reinforcement Learning 奖励——机器引导、自定进度的强化学习

Adaptive Agents and Multi-Agent Systems Pub Date : 2023-05-25 DOI: 10.5555/3545946.3598964

Cevahir Köprülü, U. Topcu

引用次数: 2

Online Influence Maximization under Decreasing Cascade Model 递减级联模型下的在线影响最大化

Adaptive Agents and Multi-Agent Systems Pub Date : 2023-05-19 DOI: 10.5555/3545946.3598895

Fang-yuan Kong, Jize Xie, Baoxiang Wang, Tao Yao, Shuai Li

引用次数: 1