Independent from the still ongoing research in measuring individual intelligence, we anticipate and provide a framework for measuring collective intelligence. Collective intelligence refers to the idea that several individuals can collaborate in order to achieve high levels of intelligence. We present thus some ideas on how the intelligence of a group can be measured and simulate such tests. We will however focus here on groups of artificial intelligence agents (i.e., machines). We will explore how a group of agents is able to choose the appropriate problem and to specialize for a variety of tasks. This is a feature which is an important contributor to the increase of intelligence in a group (apart from the addition of more agents and the improvement due to common decision making). Our results reveal some interesting results about how (collective) intelligence can be modeled, about how collective intelligence tests can be designed and about the underlying dynamics of collective intelligence. As it will be useful for our simulations, we provide also some improvements of the threshold allocation model originally used in the area of swarm intelligence but further generalized here.

In soccer, scoring goals is a fundamental objective which depends on many conditions and constraints. Considering the RoboCup soccer 2D-simulator, this paper presents a data mining-based decision system to identify the best time and direction to kick the ball towards the goal to maximize the overall chances of scoring during a simulated soccer match. Following the CRISP-DM methodology, data for modeling were extracted from matches of major international tournaments (10691 kicks), knowledge about soccer was embedded via transformation of variables and a Multilayer Perceptron was used to estimate the scoring chance. Experimental performance assessment to compare this approach against previous LDA-based approach was conducted from 100 matches. Several statistical metrics were used to analyze the performance of the system and the results showed an increase of 7.7% in the number of kicks, producing an overall increase of 78% in the number of goals scored.

In this article we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an interface to hundreds of Atari 2600 game environments, each one different, interesting, and designed to be a challenge for human players. ALE presents significant research challenges for reinforcement learning, model learning, model-based planning, imitation learning, transfer learning, and intrinsic motivation. Most importantly, it provides a rigorous testbed for evaluating and comparing approaches to these problems. We illustrate the promise of ALE by developing and benchmarking domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning. In doing so, we also propose an evaluation methodology made possible by ALE, reporting empirical results on over 55 different games. All of the software, including the benchmark agents, is publicly available.

In electronic marketplaces, after each transaction buyers will rate the products provided by the sellers. To decide the most trustworthy sellers to transact with, buyers rely on trust models to leverage these ratings to evaluate the reputation of sellers. Although the high effectiveness of different trust models for handling unfair ratings have been claimed by their designers, recently it is argued that these models are vulnerable to more intelligent attacks, and there is an urgent demand that the robustness of the existing trust models has to be evaluated in a more comprehensive way. In this work, we classify the existing trust models into two broad categories and propose an extendable e-marketplace testbed to evaluate their robustness against different unfair rating attacks comprehensively. On top of highlighting the robustness of the existing trust models for handling unfair ratings is far from what they were claimed to be, we further propose and validate a novel combination mechanism for the existing trust models, Discount-then-Filter, to notably enhance their robustness against the investigated attacks.

We consider how selfish agents are likely to share revenues derived from maintaining connectivity between important network servers. We model a network where a failure of one node may disrupt communication between other nodes as a cooperative game called the vertex Connectivity Game (CG). In this game, each agent owns a vertex, and controls all the edges going to and from that vertex. A coalition of agents wins if it fully connects a certain subset of vertices in the graph, called the primary vertices. Power indices measure an agent's ability to affect the outcome of the game. We show that in our domain, such indices can be used to both determine the fair share of the revenues an agent is entitled to, and identify significant possible points of failure affecting the reliability of communication in the network. We show that in general graphs, calculating the Shapley and Banzhaf power indices is #P-complete, but suggest a polynomial algorithm for calculating them in trees. We also investigate finding stable payoff divisions of the revenues in CGs, captured by the game theoretic solution of the core, and its relaxations, the epsilon-core and least core. We show a polynomial algorithm for computing the core of a CG, but show that testing whether an imputation is in the epsilon-core is coNP-complete. Finally, we show that for trees, it is possible to test for epsilon-core imputations in polynomial time.

In this article we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an interface to hundreds of Atari 2600 game environments, each one different, interesting, and designed to be a challenge for human players. ALE presents significant research challenges for reinforcement learning, model learning, model-based planning, imitation learning, transfer learning, and intrinsic motivation. Most importantly, it provides a rigorous testbed for evaluating and comparing approaches to these problems. We illustrate the promise of ALE by developing and benchmarking domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning. In doing so, we also propose an evaluation methodology made possible by ALE, reporting empirical results on over 55 different games. All of the software, including the benchmark agents, is publicly available.

The random drift particle swarm optimization (RDPSO) algorithm, inspired by the free electron model in metal conductors placed in an external electric field, is presented, systematically analyzed and empirically studied in this paper. The free electron model considers that electrons have both a thermal and a drift motion in a conductor that is placed in an external electric field. The motivation of the RDPSO algorithm is described first, and the velocity equation of the particle is designed by simulating the thermal motion as well as the drift motion of the electrons, both of which lead the electrons to a location with minimum potential energy in the external electric field. Then, a comprehensive analysis of the algorithm is made, in order to provide a deep insight into how the RDPSO algorithm works. It involves a theoretical analysis and the simulation of the stochastic dynamical behavior of a single particle in the RDPSO algorithm. The search behavior of the algorithm itself is also investigated in detail, by analyzing the interaction between the particles. Some variants of the RDPSO algorithm are proposed by incorporating different random velocity components with different neighborhood topologies. Finally, empirical studies on the RDPSO algorithm are performed by using a set of benchmark functions from the CEC2005 benchmark suite. Based on the theoretical analysis of the particle's behavior, two methods of controlling the algorithmic parameters are employed, followed by an experimental analysis on how to select the parameter values, in order to obtain a good overall performance of the RDPSO algorithm and its variants in real-world applications. A further performance comparison between the RDPSO algorithms and other variants of PSO is made to prove the efficiency of the RDPSO algorithms.

Many real-world planning domains, including those used in common benchmark problems, are based on multiagent scenarios. It has long been recognised that breaking down such problems into sub-problems for individual agents may help reduce overall planning complexity. This kind of approach is especially effective in domains where interaction between agents is limited. In this paper we present a fully centralised, offline, sequential, total-order planning algorithm for solving classical planning problems based on this idea. This algorithm consists of an automated decomposition process and a heuristic search method designed specifically for decomposed domains. The decomposition method is part of a preprocessing step and can be used to determine the 'multiagent nature' of a planning problem prior to actual plan search. The heuristic search strategy is shown to effectively exploit any decompositions that are found and performs significantly better than current approaches on loosely coupled domains.

When multiple agents want to maintain temporal information, they can employ a Multiagent Simple Temporal Network (MaSTN). Recent work has shown that the constraints in a MaSTN can be efficiently propagated by enforcing partial path consistency (PPC) with a distributed algorithm. However, new temporal constraints may arise continually due to ongoing plan construction or execution, the decisions of other agents, and other exogenous events. For these new constraints, propagation is again required to re-establish PPC. Because the affected part of the network may be small, one typically wants to exploit the similarities between the new and previous version of the MaSTN. To this end, we propose two new distributed algorithms for incrementally maintaining PPC. The first is inspired by TriSTP, the seminal PPC algorithm for STNs; the second is a distributed version of IPPC, which represents the current state of the art for incrementally enforcing PPC in a centralized setting. The worst-case time performance of these algorithms is similar to their centralized counterparts. We empirically compare our distributed algorithms, analyzing their performance under various assumptions, and demonstrate significant speedup over their centralized counterparts.

We address efficient planning of maintenance activities in infrastructural networks, inspired by the real-world problem of servicing a highway network. A road authority is responsible for the quality, throughput and maintenance costs of the network, while the actual maintenance is performed by autonomous, third-party contractors. From a (multi-agent) planning and scheduling perspective, many interesting challenges can be identified. First, planned maintenance activities might have an uncertain duration due to unexpected delays. Second, since maintenance activities influence the traffic flow in the network, careful coordination of the planned activities is required in order to minimise their impact on the network throughput. Third, as we are dealing with selfish agents in a private-values setting, the road authority faces an incentive-design problem to truthfully elicit agent costs, complicated by the fact that it needs to balance multiple objectives. The main contributions of this work are: 1) multi-agent coordination on a network level through a novel combination of planning under uncertainty and dynamic mechanism design, applied to real-world problems, 2) accurate modelling and solving of maintenance-planning problems and 3) empirical exploration of the complexities that arise in these problems. We introduce a formal model of the problem domain, present experimental insights and identify open challenges for both the planning and scheduling as well as the mechanism design communities.