Interactive Narrative is an emerging application of automated planning, in which a planning domain is used to generate a consistent chain of narrative actions that constitute a plot structure. The task of creating narrative planning domains has been identified as a bottleneck which is hampering further development of the field. This stems from the difficulties faced by humans authoring such planning

We propose a new method for learning compact state representations and policies separately but simultaneously for policy approximation in vision-based applications such as Atari games. Approaches based on deep reinforcement learning typically map pixels directly to actions to enable end-to-end training. Internally, however, the deep neural network bears the responsibility of both extracting useful

Computational argumentation has taken a predominant place in the modeling of negotiation dialogues over the last years. A competent agent participating in a negotiation process is expected to decide its next move taking into account an, often incomplete, model of its opponent. This work provides a complete computational account of argumentation-based negotiation under incomplete opponent profiles.

Microscopic agent-based traffic simulation is an important tool for the efficient and safe resolution of various traffic challenges accompanying the introduction of autonomous vehicles on the roads. Both the variety of questions that can be asked and the quality of answers provided by simulations, however, depend on the underlying models. In mixed traffic, the two most critical models are the models

In multi-type resource allocation (MTRA) problems, there are \(d\ge 2\) types of items, and n agents who each demand one unit of items of each type and have strict linear preferences over bundles consisting of one item of each type. For MTRAs with indivisible items, our first result is an impossibility theorem that is in direct contrast to the single type (\(d=1\)) setting: no mechanism, the output

In Coalition Structure Generation (CSG), one seeks to form a partition of a given set of agents into coalitions such that the sum of the values of each coalition is maximized. This paper introduces a model for Probabilistic CSG (PCSG), which extends the standard CSG model to account for the stochastic nature of the environment, i.e., when some of the agents considered at start may be finally defective

Recently, it has been proposed that Game Description Language (GDL) could be used to define negotiation domains. This would open up an entirely new, declarative, approach to Automated Negotiations in which a single algorithm could negotiate over any domain, as long as that domain is expressible in GDL. However, until now, the feasibility of this approach has only been demonstrated on a few toy-world

Since its dawn as a discipline, Artificial Intelligence (AI) has focused on mimicking the human mental processes. As AI applications matured, the interest for employing them into real-world complex systems (i.e., coupling AI with Cyber-Physical Systems—CPS) kept increasing. In the last decades, the multi-agent systems (MAS) paradigm has been among the most relevant approaches fostering the development

Police officers conduct routine patrols and perform tasks in response to reported incidents. The importance of each task varies from low (e.g. noise complaint) to high (e.g. murder). The workload associated with each task, indicating the amount of work to be completed for the incident to be processed, may vary as well. Multiple officers with heterogeneous skills may work together on important tasks

Multi-agent systems (MAS) represent a distributed computing paradigm well suited to tackle today’s challenges in the field of the Internet of Things (IoT). Both share many similarities such as the interconnection of distributed devices and their cooperation. The combination of MAS and IoT would allow the transfer of the experience gained in MAS research to the broader range of IoT applications. The

Group decisions are often complicated by a deadline. For example, in committee hiring decisions the deadline might be the next start of a budget, or the beginning of a semester. It may be that if no candidate is supported by a strong majority, the default is to hire no one - an option that may cost dearly. As a result, committee members might prefer to agree on a reasonable, if not necessarily the

A computational system is called autonomous if it is able to make its own decisions, or take its own actions, without human supervision or control. The capability and spread of such systems have reached the point where they are beginning to touch much of everyday life. However, regulators grapple with how to deal with autonomous systems, for example how could we certify an Unmanned Aerial System for

Image sharing is a service offered by many online social networks. In order to preserve privacy of images, users need to think through and specify a privacy setting for each image that they upload. This is difficult for two main reasons: first, research shows that many times users do not know their own privacy preferences, but only become aware of them over time. Second, even when users know their

In many distributed systems, from cloud to sensor networks, different configurations impact system performance, while strongly depending on the network topology. Hence, topological changes may entail costly reconfiguration and optimisation processes. This paper proposes a multi-agent solution for recovering networks from node failures. To preserve the network topology, the proposed approach relies

We consider tournaments played by a set of players in order to establish a ranking among them. We introduce the notion of irrelevant match, as a match that does not influence the ultimate ranking of the involved parties. After discussing the basic properties of this notion, we seek out tournaments that have no irrelevant matches, focusing on the class of tournaments where each player challenges each

Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from observing its behavior on a task. It inverts RL which focuses on learning an agent’s behavior on a task based on the reward signals received. IRL is witnessing sustained attention due to promising applications in robotics, computer games, and finance, as well as in other sectors. Methods for IRL have, for

Optimal placement of charging stations for electric vehicles (EVs) is critical for providing convenient charging service to EV owners and promoting public acceptance of EVs. There has been a lot of work on EV charging station placement, yet EV drivers’ charging strategy, which plays an important role in deciding charging stations’ performance, is missing. EV drivers make choice among charging stations

One challenging problem in multiagent systems is to cooperate or compete with non-stationary agents that change behavior from time to time. An agent in such a non-stationary environment is usually supposed to be able to quickly detect the other agents’ policy during online interaction, and then adapt its own policy accordingly. This article studies efficient policy detecting and reusing techniques

Precisely when the success of artificial intelligence (AI) sub-symbolic techniques makes them be identified with the whole AI by many non-computer-scientists and non-technical media, symbolic approaches are getting more and more attention as those that could make AI amenable to human understanding. Given the recurring cycles in the AI history, we expect that a revamp of technologies often tagged as

Unfortunately, a post-galley copyediting error altered the contents of cells in the Condorcet Elections columns of the table in Footnote 7.

We introduce personalised rating, a network-based rating system where individuals, connected in a social network, decide whether or not to consume a service (e.g., a restaurant) based on the evaluations provided by their peers. We compare personalised rating with the more widely used objective rating where, instead, customers receive an aggregate evaluation of what everybody else has declared so far

This paper addresses a task in Interactive Task Learning (Laird et al. IEEE Intell Syst 32:6–21, 2017). The agent must learn to build towers which are constrained by rules, and whenever the agent performs an action which violates a rule the teacher provides verbal corrective feedback: e.g. “No, red blocks should be on blue blocks”. The agent must learn to build rule compliant towers from these corrections

The classical Stable Roommates problem is to decide whether there exists a matching of an even number of agents such that no two agents which are not matched to each other would prefer to be with each other rather than with their respectively assigned partners. We investigate Stable Roommates with complete (i.e., every agent can be matched with any other agent) or incomplete preferences, with ties

Control and manipulation are two of the most studied types of attacks on elections. In this paper, we study the complexity of control attacks on elections in which there are manipulators. We study both the case where the “chair” who is seeking to control the election is allied with the manipulators, and the case where the manipulators seek to thwart the chair. In the latter case, we see that the order

The Housing Market problem is a widely studied resource allocation problem. In this problem, each agent can only receive a single object and has preferences over all objects. Starting from an initial endowment, we want to reach a certain assignment via a sequence of rational trades. We first consider whether an object is reachable for a given agent under a social network, where a trade between two

Asymmetric distributed constraint optimization problems (ADCOPs) have emerged as an important formalism in multi-agent community due to their ability to capture personal preferences. However, the existing search-based complete algorithms for ADCOPs only exploit local knowledge to calculate lower bounds, which leads to inefficient pruning and prohibits them from solving large scale problems. On the

We consider the design of mechanisms for locating facilities on an interval. There are multiple agents on the interval, each receiving a utility determined by their distances to the facilities. The objectives considered are maximization of social welfare (sum of utilities) and egalitarian welfare (minimum utility). Agents can misreport their locations, and so we require the mechanisms to be strategyproof—no

A relevant application domain for agent-based software is given by mobile and wearable applications. In this context, the impressive progress of technologies in the last decade makes it possible to explore the use of agent-oriented programming languages and frameworks based on cognitive architectures, such as the Belief–Desire–Intention (BDI) one. Accordingly, in this paper we provide a comprehensive

The importance of Agent-Based Simulation (ABS) as scientific method to generate data for scientific models in general and for informed policy decisions in particular has been widely recognised. However, the important technique of code testing of implementations like unit testing has not generated much research interested so far. As a possible solution, in previous work we have explored the conceptual

A principal needs to elicit the true value of an object she owns from an agent who has a unique ability to compute this information. The principal cannot verify the correctness of the information, so she must incentivize the agent to report truthfully. Previous works coped with this unverifiability by employing two or more information agents and awarding them according to the correlation between their

Learning models of user behaviour is an important problem that is broadly applicable across many application domains requiring human–robot interaction. In this work, we show that it is possible to learn generative models for distinct user behavioural types, extracted from human demonstrations, by enforcing clustering of preferred task solutions within the latent space. We use these models to differentiate

To achieve system-level properties of a multiagent system, the behavior of individual agents should be controlled and coordinated. One way to control agents without limiting their autonomy is to enforce norms by means of sanctions. The dynamicity and unpredictability of the agents’ interactions in uncertain environments, however, make it hard for designers to specify norms that will guarantee the achievement

We study a variant of the multi-agent path finding (MAPF) problem in which the group of agents are required to stay connected with a supervising base station throughout the execution. In addition, we consider the problem of covering an area with the same connectivity constraint. We show that both problems are PSPACE-complete on directed and undirected topological graphs while checking the existence

Decentralized policies for information gathering are required when multiple autonomous agents are deployed to collect data about a phenomenon of interest when constant communication cannot be assumed. This is common in tasks involving information gathering with multiple independently operating sensor devices that may operate over large physical distances, such as unmanned aerial vehicles, or in communication

Local search algorithms are widely applied in solving large-scale Distributed constraint optimization problems (DCOPs) where each agent holds a value assignment to its variable and iteratively makes a decision on whether to replace its assignment according to its neighbor states. However, the value assignments of their neighbors confine their search to a small space so that agents in local search algorithms

Understanding how to design agents that sustain cooperation in multi-agent systems has been a long-lasting goal in distributed artificial intelligence. Proposed solutions rely on identifying free-riders and avoiding cooperating or interacting with them. These mechanisms of social control are traditionally studied in games with linear and deterministic payoffs, such as the prisoner’s dilemma or the

We describe an approach for constraining robot autonomy based on the robot’s awareness of patterns of its human teammates’ behaviors, rather than either ignoring its teammates (which is fast but dangerous) or inferring their plans (which is safer but slow). We explore the promise, and limitations, of this approach in a series of simulated problems where an unmanned ground vehicle and its human teammates

Large teams of heterogeneous agents have the potential to solve complex multi-task problems that are intractable for a single agent working independently. However, solving complex multi-task problems requires leveraging the relative strengths of the different kinds of agents in the team. We present Stochastic TRAit-based Task Assignment (STRATA), a unified framework that models large teams of heterogeneous

It is claimed that, in the nascent ‘Cognitive Era’, intelligent systems will be trained using machine learning techniques rather than programmed by software developers. A contrary point of view argues that machine learning has limitations, and, taken in isolation, cannot form the basis of autonomous systems capable of intelligent behaviour in complex environments. In this paper, we explore the contributions

A recent survey provides convincing evidence that JADE is among the most widely used tools to develop agent-based software systems. It finds application in industrial settings and to support research, and it has been used to introduce students to software agents in various universities. This paper offers a perspective on the current state of JADE by first presenting a chronicle of the relevant events

In this paper, we propose a framework that enables a human teacher to shape a robot behaviour by interactively providing it with unlabeled instructions. We ground the meaning of instruction signals in the task-learning process, and use them simultaneously for guiding the latter. We implement our framework as a modular architecture, named TICS (Task-Instruction-Contingency-Shaping) that combines different

We develop a logic-based framework for formal specification and algorithmic verification of homogeneous and dynamic concurrent multi-agent transition systems. Homogeneity means that all agents have the same available actions at any given state and the actions have the same effects regardless of which agents perform them. The state transitions are therefore determined only by the vector of numbers of

Agents providing assistance to humans are faced with the challenge of automatically adjusting the level of assistance to ensure optimal performance. In this work, we argue that identifying the right level of assistance consists in balancing positive assistance outcomes and some (domain-dependent) measure of cost associated with assistive actions. Towards this goal, we contribute a general mathematical

Communication is a critical factor for the big multi-agent world to stay organized and productive. Recently, Deep Reinforcement Learning (DRL) has been adopted to learn the communication among multiple intelligent agents. However, in terms of the DRL setting, the increasing number of communication messages introduces two problems: (1) there are usually some redundant messages; (2) even in the case

Plurality voting is perhaps the most commonly used way to aggregate the preferences of multiple voters. Yet, there is no consensus on how people vote strategically, even in very simple settings. The purpose of this paper is to provide a comprehensive study of people’s voting behavior in various online settings under the plurality rule. We implemented voting games that replicate two common real-world

Kumbh Mela festival of India is one of the largest mass gathering event of huge religious importance all over the world. Large gatherings in these kind of religious events require rigorous monitoring and attention. Successful organization of such events requires synchronization among officials of different public departments such as police, health, security, communication, railways etc. The railway

An important research problem in artificial intelligence is how to organize multiple agents, and coordinate them, so that they can work together to solve problems. Coordinating agents in a multi-agent system can significantly affect the system’s performance—the agents can, in many instances, be organized so that they can solve tasks more efficiently, and consequently benefit collectively and individually

Learning interpretable and transferable subpolicies and performing task decomposition from a single, complex task is difficult. Such decomposition can lead to immense sample efficiency gains in lifelong learning. Some traditional hierarchical reinforcement learning techniques enforce this decomposition in a top-down manner, while meta-learning techniques require a task distribution at hand to learn

In a multiwinner election based on the Condorcet criterion, we are given a set of candidates, and a set of voters with strict preference rankings over the candidates. A committee is weakly Gehrlein stable (WGS) if each committee member is preferred to each non-member by at least half of the voters. Recently, Aziz et al. [IJCAI 2017] studied the computational complexity of finding a WGS committee of

Competitive equilibrium (CE) is a fundamental concept in market economics. Its efficiency and fairness properties make it particularly appealing as a rule for fair allocation of resources among agents with possibly different entitlements. However, when the resources are indivisible, a CE might not exist even when there is one resource and two agents with equal incomes. Recently, Babaioff and Nisan

How to form effective coalitions is an important issue in multi-agent systems. Coalition Structure Generation (\({{\mathsf {CSG}}}\)) is a fundamental problem whose formalization can encompass various applications related to multi-agent cooperation. \({{\mathsf {CSG}}}\) involves partitioning a set of agents into coalitions such that the social surplus (i.e., the sum of the values of all coalitions)

Selecting a set of alternatives based on the preferences of agents is an important problem in committee selection and beyond. Among the various criteria put forth for desirability of a committee, Pareto optimality is a minimal and important requirement. As asking agents to specify their preferences over exponentially many subsets of alternatives is practically infeasible, we assume that each agent

We introduce a new type of distributional constraints called ratio constraints, which explicitly specify the required balance among schools in two-sided matching. Since ratio constraints do not belong to the known well-behaved class of constraints called M-convex set, developing a fair and strategyproof mechanism that can handle them is challenging. We develop a novel mechanism called quota reduction

Interactive reinforcement learning provides a way for agents to learn to solve tasks from evaluative feedback provided by a human user. Previous research showed that humans give copious feedback early in training but very sparsely thereafter. In this article, we investigate the potential of agent learning from trainers’ facial expressions via interpreting them as evaluative feedback. To do so, we implemented

The state-action space of an individual agent in a multiagent team fundamentally dictates how the individual interacts with the rest of the team. Thus, how an agent is defined in the context of its domain has a significant effect on team performance when learning to coordinate. In this work we explore the trade-offs associated with these design choices, for example, having fewer agents in the team

This paper presents the formalization for a system that monitors and enforces regulative time-constrained conditional norms through sanctioning, for agent societies. The representation here has the advantage of allowing for qualitative and quantitative interval-based temporal constraints between a norm’s condition and its effect. The system possesses mechanisms for monitoring both norm compliance and

We focus on how an agent can exercise autonomy while still dependably fulfilling commitments it has made to another, despite uncertainty about outcomes of its actions and how its own objectives might evolve. Our formal semantics treats a probabilistic commitment as constraints on the actions an autonomous agent can take, rather than as promises about states of the environment it will achieve. We have

Path auction is held in a graph, where each edge stands for a commodity and the weight of this edge represents the prime cost. Bidders own some edges and make bids for their edges. The auctioneer needs to purchase a sequence of edges to form a path between two specific vertices. Path auction can be considered as a kind of combinatorial reverse auctions. Core-selecting mechanism is a prevalent mechanism

In this paper we present DALI, a distributed, collaborative multi-agent traffic signal timing system (TST) for highly dynamic traffic conditions. In DALI, intersection controllers are augmented with software agents which collaboratively adapt signal timings by considering the feedback of all controller agents that may be affected by a change. The model is based on a real-world TST and will be deployed

This paper introduces the Crossmodal Attentive Skill Learner (CASL), integrated with the recently-introduced Asynchronous Advantage Option-Critic architecture [Harb et al. in When waiting is not an option: learning options with a deliberation cost. arXiv preprint arXiv:1709.04571, 2017] to enable hierarchical reinforcement learning across multiple sensory inputs. Agents trained using our approach learn