We consider three important, non-strategyproof assignment mechanisms: Probabilistic Serial and two variants of the Boston mechanism. Under each of these mechanisms, we study the agent’s manipulation problem of determining a best response, i.e., a report that maximizes the agent’s expected utility. In particular, we consider local manipulation strategies, which are simple heuristics based on local, greedy search. We make three main contributions. First, we present results from a behavioral experiment (conducted on Amazon Mechanical Turk) which demonstrate that human manipulation strategies can largely be explained by local manipulation strategies. Second, we prove that local manipulation strategies may fail to solve the manipulation problem optimally. Third, we show via large-scale simulations that despite this non-optimality, these strategies are very effective on average. Our results demonstrate that while the manipulation problem may be hard in general, even cognitively or computationally bounded (human) agents can find near-optimal solutions almost all the time via simple local search strategies.

A key challenge in solving extensive-form games is dealing with large, or even infinite, action spaces. In games of imperfect information, the leading approach is to find a Nash equilibrium in a smaller abstract version of the game that includes only a few actions at each decision point, and then map the solution back to the original game. However, it is difficult to know which actions should be included in the abstraction without first solving the game, and it is infeasible to solve the game without first abstracting it. We introduce a method that combines abstraction with equilibrium finding by enabling actions to be added to the abstraction at run time. This allows an agent to begin learning with a coarse abstraction, and then to strategically insert actions at points that the strategy computed in the current abstraction deems important. The algorithm can quickly add actions to the abstraction while provably not having to restart the equilibrium finding. It enables anytime convergence to a Nash equilibrium of the full game even in infinite games. Experiments show it can outperform fixed abstractions at every stage of the run: early on it improves as quickly as equilibrium finding in coarse abstractions, and later it converges to a better solution than does equilibrium finding in fine-grained abstractions.

Belief revision is concerned with incorporating new information into a pre-existing set of beliefs. When the new information comes from another agent, we must first determine if that agent should be trusted. In this paper, we define trust as a pre-processing step before revision. We emphasize that trust in an agent is often restricted to a particular domain of expertise. We demonstrate that this form of trust can be captured by associating a state partition with each agent, then relativizing all reports to this partition before revising.  We position the resulting family of trust-sensitive revision operators within the class of selective revision operators of Ferme and Hansson, and we examine its properties. In particular, we show how trust-sensitive revision is manipulable, in the sense that agents can sometimes have incentive to pass on misleading information.  When multiple reporting agents are involved, we use a distance function over states to represent differing degrees of trust; this ensures that the most trusted reports will be believed.

Boolean games are a game-theoretic framework in which propositional logic is used to describe agents’ goals. In this paper we investigate how agents in Boolean games can reach an efficient and fair outcome through a simple negotiation protocol. We are particularly interested in settings where agents only have incomplete knowledge about the preferences of others. After explaining how generalized possibilistic logic can be used to compactly encode such knowledge, we analyze how a lack of knowledge affects the agreement outcome. In particular, we show how knowledgeable agents can obtain a more desirable outcome than others.

We consider a setting where a team of humans oversee the coordination of multiple Unmanned Aerial Vehicles (UAVs) to perform a number of search tasks in dynamic environments that may cause the UAVs to drop out. Hence, we develop a set of multi-UAV supervisory control interfaces and a multi-agent coordination algorithm to support human decision making in this setting. To elucidate the resulting interactional issues, we compare manual and mixed-initiative task allocation in both static and dynamic environments in lab studies with 40 participants and observe that our mixed-initiative system results in lower workloads and better performance in re-planning tasks than one which only involves manual task allocation. Our analysis points to new insights into the way humans appropriate flexible autonomy.

Only knowing captures the intuitive notion that the beliefs of an agent are precisely those that follow from its knowledge base. While only knowing has a simple possible-world semantics in a single agent setting, the many agent case has turned out to be much more challenging. In a recent paper, we proposed an account which arguably extends only knowing to multiple agents in a natural way. However, the approach was limited in that the semantics cannot deal with infinitary notions such as common knowledge. In this work, we lift that serious limitation to obtain a first-order language with only knowing and common knowledge, allowing us to study the interaction between these notions for the very first time. By adding a simple form of public announcement, we then demonstrate how the muddy children puzzle can be cast in terms of logical implications given what is only known initially.

Exploiting parallelism is a key strategy for speeding up computation. However, on hard combinatorial problems, such a strategy has been surprisingly challenging due to the intricate variable interactions.We introduce a novel way in which parallelism can be used to exploit hidden structure of hard combinatorial problems. Our approach complements divide-and-conquer and portfolio approaches. We evaluate our approach on the minimum set basis problem: a core combinatorial problem with a range of applications in optimization, machine learning, and system security. We also highlight a novel sustainability related application, concerning the discovery of new materials for renewable energy sources such as improved fuel cell catalysts. In our approach, a large number of smaller sub-problems are identified and solved concurrently. We then aggregate the information from those solutions, and use this information to initialize the search of a global, complete solver. We show that this strategy leads to a substantial speed-up over a sequential approach, since the aggregated sub-problem solution information often provides key structural insights to the complete solver. Our approach also greatly outperforms state-of-the-art incomplete solvers in terms of solution quality. Our work opens up a novel angle for using parallelism to solve hard combinatorial problems.

We introduce the study of adversarial effects on wisdom of the crowd phenomena. In particular, we examine the ability of an adversary to influence a social network so that the majority of nodes are convinced by a falsehood, using its power to influence a certain fraction, μ < 0.5 of N experts. Can a bad restaurant make a majority of the overall network believe in the quality of that restaurant by misleading a certain share of food critics into believing its food is good, and use the influence of those experts to make a majority of the overall network to believe in the quality of that restaurant? We are interested in providing an agent, which does not necessarily know the graph structure nor who the experts are, to determine the true value of a binary property using a simple majority. We prove bounds on the social graph's maximal degree, which ensure that with a high probability the adversary will fail (and the majority vote will coincide with the true value) when it can choose who the experts are, while each expert communicates the true value with probability p > 0.5. When we examine expander graphs as well as random graphs we prove such bounds even for stronger adversaries, who are able to pick and choose not only who the experts are, but also which ones of them would communicate the wrong values, as long as their proportion is 1-p. Furthermore, we study different propagation models and their effects on the feasibility of obtaining the true value for different adversary types.

The paper faces the problem of plan repair in presence of numeric information, by providing a new method for the intelligent selection of numeric macro actions. The method relies on a generalization of deordering, extended with new conditions accounting for dependencies and threats implied by the numeric components. The deordering is used as a means to infer (hopefully) minimal ordering constraints then used to extract independent and informative macro actions. Each macro aims at compactly representing a sub-solution for the overall planning problem. To verify the feasibility of the approach, the paper reports experiments in various domains from the International Planning Competition% measuring the performance of the new strategy using two state of the art numeric planning systems; i.e., Colin Metric-FF. Results show (i) the competitiveness of the strategy in terms of coverage, time and quality of the resulting plans wrt current approaches, and (ii) the actual independence from the planner employed.

Despite some success of Perfect Information Monte Carlo Sampling (PIMC) in imperfect information games in the past, it has been eclipsed by other approaches in recent years. Standard PIMC has well-known shortcomings in the accuracy of its decisions, but has the advantage of being simple, fast, robust and scalable, making it well-suited for imperfect information games with large state-spaces. We propose Presumed Value PIMC resolving the problem of overestimation of opponent's knowledge of hidden information in future game states. The resulting AI agent was tested against human experts in Schnapsen, a Central European 2-player trick-taking card game, and performs above human expert-level.