Security games involving the allocation of multiple security resources to defend multiple targets generally have an exponential number of pure strategies for the defender. One method that has been successful in addressing this computational issue is to instead directly compute the marginal probabilities with which the individual resources are assigned (first pursued by Kiekintveld et al. (2009)). However, in sufficiently general settings, there exist games where these marginal solutions are not implementable, that is, they do not correspond to any mixed strategy of the defender. In this paper, we examine security games where the defender tries to monitor the vertices of a graph, and we show how the type of graph, the type of schedules, and the type of defender resources affect the applicability of this approach. In some settings, we show the approach is applicable and give a polynomial-time algorithm for computing an optimal defender strategy; in other settings, we give counterexample games that demonstrate that the approach does not work, and prove NP-hardness results for computing an optimal defender strategy.

We present a novel negotiation protocol to facilitate energy exchange between off-grid homes that are equipped with renewable energy generation and electricity storage. Our protocol imposes restrictions over negotiation such that it reduces the complex interdependent multi-issue negotiation to one where agents have a strategy profile in subgame perfect Nash equilibrium. We show that our negotiation protocol is tractable, concurrent, scalable and leads to Pareto-optimal outcomes in a decentralised manner. We empirically evaluate our protocol and show that, in this instance, a society of agents can (i) improve the overall utilities by 14% and (ii) reduce their overall use of the batteries by 37%.

In many logic-based BDI agent programming languages, plan selection involves inferencing over some underlying knowledge representation. While context-sensitive plan selection facilitates the development of flexible, declarative programs, the overhead of evaluating repeated queries to the agent's beliefs and goals can result in poor run time performance. In this paper we present an approach to multi-cycle query caching for logic-based BDI agent programming languages. We extend the abstract performance model presented in (Alechina et al. 2012) to quantify the costs and benefits of caching query results over multiple deliberation cycles. We also present results of experiments with prototype implementations of both single- and multi-cycle caching in three logic-based BDI agent platforms, which demonstrate that significant performance improvements are achievable in practice.

Commitments help model interactions in multiagent systems in a computationally realizable yet high-level manner without compromising the autonomy and heterogeneity of the member agents. Recent work shows how to combine commitments with goals and apply planning methods to enable agents to determine their actions. However, previous approaches to modeling commitments are confined to propositional representations, which limits their applicability in practical cases. We propose a first-order representation and reasoning technique that accommodates templatic commitments and goals that may be applied repeatedly with differing bindings for domain objects. Doing so not only leads to a more perspicuous modeling, but also supports many practical patterns.

The Multiagent Disjunctive Temporal Problem (MaDTP) is a general constraint-based formulation for scheduling problems that involve interdependent agents. Decoupling agents' interdependent scheduling problems, so that each agent can manage its schedule independently, requires agents to adopt additional local constraints that effectively subsume their interdependencies. In this paper, we present the first algorithm for decoupling MaDTPs. Our distributed algorithm is provably sound and complete. Our experiments show that the relative efficiency of using temporal decoupling to find solution spaces for MaDTPs, compared to algorithms that find complete solution spaces, improves with the interconnectedness between agents schedules, leading to orders of magnitude relative speeedup. However, decoupling by its nature restricts agents' scheduling flexibility; we define novel flexibility metrics for MaDTPs, and show empirically how the flexibility sacrificed depends on the degree of coupling between agents' schedules.

Many negotiations in the real world are characterized by incomplete information, and participants' success depends on their ability to reveal information in a way that facilitates agreement without compromising the individual gains of agents. This paper presents a novel agent design for repeated negotiation in incomplete information settings that learns to reveal information strategically during the negotiation process. The agent used classical machine learning techniques to predict how people make and respond to offers during the negotiation, how they reveal information and their response to potential revelation actions by the agent. The agent was evaluated empirically in an extensive empirical study spanning hundreds of human subjects. Results show that the agent was able to outperform people. In particular, it learned (1) to make offers that were beneficial to people while not compromising its own benefit; (2) to incrementally reveal information to people in a way that increased its expected performance. The approach generalizes to new settings without the need to acquire additional data. This work demonstrates the efficacy of combining machine learning with opponent modeling techniques towards the design of computer agents for negotiating with people in settings of incomplete information.

Manipulation, bribery, and control are well-studied ways of changing the outcome of an election. Many voting systems are, in the general case, computationally resistant to some of these manipulative actions. However when restricted to single-peaked electorates, these systems suddenly become easy to manipulate. Recently, Faliszewski, Hemaspaandra, and Hemaspaandra studied the complexity of dishonest behavior in nearly single-peaked electorates. These are electorates that are not single-peaked but close to it according to some distance measure. In this paper we introduce several new distance measures regarding single-peakedness. We prove that determining whether a given profile is nearly single-peaked is NP-complete in many cases. For one case we present a polynomial-time algorithm. Furthermore, we explore the relations between several notions of nearly single-peakedness.

Pathfinding for a single agent is the problem of planning a route from an initial location to a goal location in an environment, going around obstacles. Pathfinding for multiple agents also aims to plan such routes for each agent, subject to different constraints, such as restrictions on the length of each path or on the total length of paths, no self-intersecting paths, no intersection of paths/plans, no crossing/meeting each other. It also has variations for finding optimal solutions, e.g., with respect to the maximum path length, or the sum of plan lengths. These problems are important for many real-life applications, such as motion planning, vehicle routing, environmental monitoring, patrolling, computer games. Motivated by such applications, we introduce a formal framework that is general enough to address all these problems: we use the expressive high-level representation formalism and efficient solvers of the declarative programming paradigm Answer Set Programming. We also introduce heuristics to improve the computational efficiency and/or solution quality. We show the applicability and usefulness of our framework by experiments, with randomly generated problem instances on a grid, on a real-world road network, and on a real computer game terrain.

Belief change is an important research topic in AI. It becomes more perplexing in multi-agent settings, since the action of an agent may be partially observable to other agents. In this paper, we present a general approach to reasoning about actions and belief change in multi-agent settings. Our approach is based on a multi-agent extension to the situation calculus, augmented by a plausibility relation over situations and another one over actions, which is used to represent agents' different perspectives on actions. When an action is performed, we update the agents' plausibility order on situations by giving priority to the plausibility order on actions, in line with the AGM approach of giving priority to new information. We show that our notion of belief satisfies KD45 properties. As to the special case of belief change of a single agent, we show that our framework satisfies most of the classical AGM, KM, and DP postulates. We also present properties concerning the change of common knowledge and belief of a group of agents.

We consider multi-agent settings where a set of agents want to take a collective decision, based on their preferences over the possible candidate options. While agents have their initial inclination, they may interact and influence each other, and therefore modify their preferences, until hopefully they reach a stable state and declare their final inclination. At that point, a voting rule is used to aggregate the agents’ preferences and generate the collective decision. Recent work has modeled the influence phenomenon in the case of voting over a single issue. Here we generalize this model to account for preferences over combinatorially structured domains including several issues. We propose a way to model influence when agents express their preferences as CP-nets. We define two procedures for aggregating preferences in this scenario, by interleaving voting and influence convergence, and study their resistance to bribery.