Skip to main content
main-content

Über dieses Buch

These transactions publish research in computer-based methods of computational collective intelligence (CCI) and their applications in a wide range of fields such as the semantic Web, social networks, and multi-agent systems. TCCI strives to cover new methodological, theoretical and practical aspects of CCI understood as the form of intelligence that emerges from the collaboration and competition of many individuals (artificial and/or natural). The application of multiple computational intelligence technologies, such as fuzzy systems, evolutionary computation, neural systems, consensus theory, etc., aims to support human and other collective intelligence and to create new forms of CCI in natural and/or artificial systems. This twenty-eight issue is a special issue with 11 selected papers from the International Conference on Agents and Artificial Intelligence, ICAART 2016 and 2017 editions.

Inhaltsverzeichnis

Frontmatter

A New Approach for Learning User Preferences for a Ridesharing Application

Abstract
Ridesharing has the potential to relieve some transportational issues such as traffic congestion, pollution and high travel costs. In this paper, we focus on the process of matching drivers and prospective riders more effectively, which is a crucial challenge in ridesharing. A novel approach is proposed in ride-matching which involves learning user preferences regarding the desirability of a choice of matching; this could then maintain high user satisfaction, thus encouraging repeat usage of the system. An SVM inspired method is developed which is able to learn a scoring function from a set of pairwise comparisons, and predicts the satisfaction degree of the user with respect to specific matches. To assess the proposed approach, we conducted some experiments on a commercial ridesharing data set. We compare the proposed approach with five rival strategies and methods, and the results clearly show the merits of our approach.
Mojtaba Montazery, Nic Wilson

An Altruistic-Based Utility Function for Group Recommendation

Abstract
Preference aggregation strategies, that are inspired by economic models of decision makers, typically assume that the individual preferences of the group members depend only on their own individual evaluations of the considered items. In this direction, group recommendation algorithms rely on such standard aggregation techniques that do not consider the possibility of evaluating social interactions and influences among group’s members, as well as their personalities, which are, indeed, crucial factors in the group’s decision-making process, especially regarding small groups. On the contrary, the laboratory data have encouraged the development of models of other-regarding preferences since altruism, fairness, and reciprocity strongly motivate many people. In this paper, starting from a utility function from the literature, which combines the user personal evaluation of an item with the ones of the other group members, we propose a group recommendation method that takes into account altruism. Such function models the level of a user’s altruistic behavior starting from his/her agreeableness personality trait. Once such utility values are evaluated, the goal is to recommend items that maximize the social welfare. Performance is evaluated with a pilot study and compared with respect to Least Misery. Results showed that while for groups of two people Least Misery performs slightly better, in the other cases the two methods are comparable.
Silvia Rossi, Francesco Cervone, Francesco Barile

Two-Stage Reinforcement Learning Algorithm for Quick Cooperation in Repeated Games

Abstract
People often learn their behavior from its outcome, e.g., success and failure. Also, in the real world, people are not alone and many interactions occur among people every day. To model such learning and interactions, let us consider reinforcement learning agents playing games. Many researchers have studied a lot of reinforcement learning algorithms to obtain good strategies in games. However, most of the algorithms are “suspicious”, i.e., focusing on how to escape from being exploited by greedy opponents. Therefore, it takes long time to establish cooperation among such agents. On the other hand, if the agents are “innocent”, i.e., prone to trust others, they establish cooperation easily but are exploited by acquisitive opponents. In this work, we propose an algorithm that uses two complementary, “innocent” and “suspicious” algorithms in the early and the late stage, respectively. The algorithm allows the agent to cooperate with good associates quickly as well as treat greedy opponents well. The experiments in ten games showed us that the proposed algorithm successfully learned good strategies quickly in nine games.
Wataru Fujita, Koichi Moriyama, Ken-ichi Fukui, Masayuki Numao

Recursive Reductions of Action Dependencies for Coordination-Based Multiagent Planning

Abstract
Currently the most efficient distributed multiagent planning scheme for deterministic models is based on coordination of local agents’ plans. In such a scheme, behavior of other agents is modeled using projections of their actions stripped of all private information. The planning scheme does not require any additional information, however using such can be beneficial for planning efficiency. Dependencies among the projected public actions caused by sequences of local private actions represent one particular type of such information.
In this work, we formally define several types of internal dependencies of multiagent planning problems and provide an algorithmic approach how to extract the internally dependent actions during multiagent planning. We show how to take an advantage of the computed dependencies by means of reducing the multiagent planning problems and analyze worst-case privacy leakage caused by the used dependencies. We integrate the reduction method into a distributed multiagent planner and summarize other efficiency improving techniques used in the planner. We experimentally show strong reduction of majority of standard multiagent benchmarks and nearly doubling of solved problems in comparison to a variant of a planner without the reductions. The efficiency of the method is demonstrated by winning in a recent competition of distributed multiagent planners.
Jan Tožička, Jan Jakubův, Antonín Komenda

Controlling a Single Transport Robot in a Flexible Job Shop Environment by Hybrid Metaheuristics

Abstract
In robotic systems, the control of some elements such as transport robot has some difficulties when planning operations dynamically. The Flexible Job Shop scheduling Problem with Transportation times and a Single Robot (FJSPT-SR) is a generalization of the classical Job Shop scheduling Problem (JSP) where a set of jobs additionally have to be transported between machines by a single transport robot. Hence, the FJSPT-SR is more computationally difficult than the JSP presenting two NP-hard problems simultaneously: the flexible job shop scheduling problem and the robot routing problem. This paper proposes a hybrid metaheuristic approach based on clustered holonic multiagent model for the FJSPT-SR. Firstly, a scheduler agent applies a Neighborhood-based Genetic Algorithm (NGA) for a global exploration of the search space. Secondly, a set of cluster agents uses a tabu search technique to guide the research in promising regions. Computational results are presented using benchmark data instances from the literature of FJSPT-SR. New upper bounds are found, showing the effectiveness of the presented approach.
Houssem Eddine Nouri, Olfa Belkahla Driss, Khaled Ghédira

Can Evolution Strategies Benefit from Shrinkage Estimators?

Abstract
Evolution strategies are evolutionary algorithms usually applied for solving continuous optimization tasks. As they rely on mutation as one of the main search operators, the control and the adaptation of this process is of high importance. This paper discusses the covariance matrix adaptation in evolution strategies, a central and essential mechanism for the search. The current form bases the estimation of the covariance matrix on small samples sizes compared to the search space dimension which is known to be problematic. This leads to the question, whether the performance of the evolutionary algorithms could be improved if other estimators were utilized. In statistics, several alternative approaches have been considered. Up to now, they have only been seldom applied in evolutionary computation. The paper investigates whether evolution strategies may benefit from linear shrinkage estimators. Several shrinkage targets are considered, integrated in the so-called CMSA-ES, and analyzed experimentally with a special focus on the shrinkage intensity.
Silja Meyer-Nieberg, Erik Kropat

An Emotional Multi-personality Architecture for Intelligent Conversational Agents

Abstract
Personal assistants and chatterbots represent an historical and growing application field in artificial intelligence. This paper presents a novel architecture to the problem of humanizing conversational agents by designing believable and unforgettable characters who exhibit various salient emotions in the flow of conversations. The proposed architecture is based on a multi-personality approach where each agent implements a facet of its identity, each one with its own pattern of perceiving and interacting with the user. In order to select an appropriate response from all the candidates, we use an emotion-based selection algorithm. Our first experiments show that a conversational multi-personality character with emotion selection performs better in terms of user engagement than a neutral mono-personality one.
Jean-Claude Heudin

Towards General Cooperative Game Playing

Abstract
Attempts to develop generic approaches to game playing have been around for several years in the field of Artificial Intelligence. However, games that involve explicit cooperation among otherwise competitive players – cooperative negotiation games – have not been addressed by current approaches. Yet, such games provide a much richer set of features, related with social aspects of interactions, which make them appealing for envisioning real-world applications. This work proposes a generic agent architecture – Alpha – to tackle cooperative negotiation games, combining elements such as search strategies, negotiation, opponent modeling and trust management. The architecture is then validated in the context of two different games that fall in this category – Diplomacy and Werewolves. Alpha agents are tested in several scenarios, against other state-of-the-art agents. Besides highlighting the promising performance of the agents, the role of each architectural component in each game is assessed.
João Marinheiro, Henrique Lopes Cardoso

Comparing the Effects of Disturbances in Self-adaptive Systems - A Generalised Approach for the Quantification of Robustness

Abstract
Self-adaptation and self-organisation (SASO) are increasingly used in information and communication technology to master complexity and keep the administrative effort at an acceptable level. However, using SASO mechanisms is not an end in itself – the primary goal is typically to allow for a higher autonomy of systems in order to react appropriately to disturbances and dynamics in the environmental conditions. We refer to this goal as achieving “robustness”. During design-time, engineers have different possibilities to develop SASO mechanisms for an underlying control problem. When deciding which path to follow, an analysis of the inherent robustness of possible solutions is necessary. In this article, we present a novel quantification method for robustness that provides the basis to compare different control strategies in similar conditions.
Sven Tomforde, Jan Kantert, Christian Müller-Schloer, Sebastian Bödelt, Bernhard Sick

Analysis of Perceived Helpfulness in Adaptive Autonomous Agent Populations

Abstract
Adaptive autonomy allows agents to change their autonomy levels based on circumstances, e.g. when they decide to rely upon one another for completing tasks. In this paper, two configurations of agent models for adaptive autonomy are discussed. In the former configuration, the adaptive autonomous behavior is modeled through the willingness of an agent to assist others in the population. An agent that completes a high number of tasks, with respect to a predefined threshold, increases its willingness, and vice-versa. Results show that, agents complete more tasks when they are willing to give help, however the need for such help needs to be low. Agents configured to be helpful will perform well among alike agents. The second configuration extends the first by adding the willingness to ask for help. Furthermore, the perceived helpfulness of the population and of the agent asking for help are used as input in the calculation of the willingness to give help. Simulations were run for three different scenarios. (i) A helpful agent which operates among an unhelpful population, (ii) an unhelpful agent which operates in a helpful populations, and (iii) a population split in half between helpful and unhelpful agents. Results for all scenarios show that, by using such trait of the population in the calculation of willingness and given enough interactions, helpful agents can control the degree of exploitation by unhelpful agents.
Mirgita Frasheri, Baran Çürüklü, Mikael Ekström

Evaluating Task-Allocation Strategies for Emergency Repair in MAS

Abstract
Nowadays, many systems are connected through networks. System of systems (SOSs) of this type can be regarded as multi-agent systems (MASs). These SoSs or MASs are robust against system failures because a failure of a system does not immediately mean the total failure of the whole system. In this paper, we consider a repairing problem of MASs where causes of future agent failures have to be removed within a limited time, and some agents become out of order if not repaired. In our simulation scenarios, many causes of future agent failures in MASs are found simultaneously and consecutively owing to large-scale disasters. In order to effectively repair them and reduce the number of agent failures, task-allocation strategies for emergency repair are extremely important. This paper compares five task-allocation algorithms in emergency situations: independent unit MAS algorithm, centralized algorithm, distributed algorithm, centralized algorithm with replanning, and distributed algorithm with replanning.
Hisashi Hayashi

Backmatter

Weitere Informationen

Premium Partner

    Bildnachweise