Computational social choice literature has successfully studied the complexity of manipulation in variousvoting systems. However, the existing modelsof coalitional manipulation view the manipulatingcoalition as an exogenous input, ignoring thequestion of the coalition formation process. While such analysis is useful as a first approximation, a richer framework is required to model voting manipulationin the real world more accurately, and, inparticular, to explain how a manipulating coalitionarises and chooses its action. In this paper, we apply tools from cooperative game theory to developa model that considers the coalition formation processand determines which coalitions are likely toform and what actions they are likely to take. We explore the computational complexity of several standard coalitional game theory solution concepts in our setting, and study the relationship betweenour model and the classic coalitional manipulation problem as well as the now-standard bribery model.

As more and more application areas require higher scalability, the study of fragments of expressive The high computational complexity of the expressive DLs with better computational properties has become an Description Logics (DLs) that underlie the important area of research. OWL standard has motivated the study of their Horn fragments of DLs, which are obtained by restricting Horn fragments, which are usually tractable in data the syntax of a DL in such a way that disjunction is not complexity and can also have lower combined complexity, expressible, were first considered in [Hustadt et al., 2005] particularly for query answering. In this paper as expressive fragments with tractable data complexity (see we provide algorithms for answering conjunctive also [Krötzsch et al., 2007]). It was later identified that they 2-way regular path queries (2CRPQs), a nontrivial can also exhibit lower combined complexity when it comes generalization of plain conjunctive queries, to query answering. Indeed, answering conjunctive queries in the Horn fragments of the DLs SHOIQ and (CQs), a kind of database-inspired queries that have become SROIQ underlying OWL 1 and OWL 2. We show the standard for querying DLs, is in ExpTime for the Horn that the combined complexity of the problem is ExpTime-complete fragment of the prominent SHIQ [Eiter et al., 2008], while it for Horn-SHOIQ and 2ExpTimecomplete is already 2ExpTime-hard for quite restricted (non Horn) fragments for the more expressive Horn-SROIQ, of SHIQ, like ALCI [Lutz, 2008] and SH [Eiter et but is PTime-complete in data complexity for both.

Learning from streaming data represents an important and challenging task. Maintaining an accurate model, while the stream goes by, requires a smart way for tracking data changes through time, originating concept drift. One way to treat this kind of problem is to resort to ensemble-based techniques. In this context, the advent of new technologies related to web and ubiquitous services call for the need of new learning approaches able to deal with structured-complex information, such as trees. Kernel methods enable the modeling of structured data in learning algorithms, however they are computationally demanding. The contribute of this work is to show how an effective ensemble-based approach can be deviced for streams of trees by optimizing the kernel-based model representation. Both efficacy and efficiency of the proposed approach are assessed for different models by using data sets exhibiting different levels and types of concept drift.

We study uniform interpolation and forgetting in the description logic ALC. Our main results are model-theoretic characterizations of uniform interpolants and their existence in terms of bisimulations, tight complexity bounds for deciding the existence of uniform interpolants, an approach to computing interpolants when they exist, and tight bounds on their size. We use a mix of model-theoretic and automata-theoretic methods that, as a by-product, also provides charachterizations of, and decision procedures for, conservative extensions.

The minimization problem for propositional formulas is an important optimization problem in the second level of the polynomial hierarchy. In general, the problem is Sigma-2-complete under Turing reductions, but restricted versions are tractable. We study the complexity of minimization for formulas in two established frameworks for restricted propositional logic: The Post framework allowing arbitrarily nested formulas over a set of Boolean connectors, and the constraint setting, allowing generalizations of CNF formulas. In the Post case, we obtain a dichotomy result: Minimization is solvable in polynomial time or coNP-hard. This result also applies to Boolean circuits. For CNF formulas, we obtain new minimization algorithms for a large class of formulas, and give strong evidence that we have covered all polynomial-time cases.

In this paper we present a new algorithm for generatively learning the structure of Markov Logic Networks. This algorithm relies on a graph of predicates, which summarizes the links existing between predicates and on relational information between ground atoms in the training database. Candidate clauses are produced by means of a heuristical variabilization technique. According to our first experiments, this approach appears to be promising.

As explained by Axelrod in his seminal work An Evolutionary Approach to Norms , punishment is a key mechanism to achieve the necessary social control and to impose social norms in a self-regulated society. In this paper, we distinguish between two enforcing mechanisms. i.e. punishment and sanction , focusing on the specific ways in which they favor the emergence and maintenance of cooperation. The key research question is to find more stable and cheaper mechanisms for norm compliance in hybrid social environments (populated by humans and computational agents). To achieve this task, we have developed a normative agent able to punish and sanction defectors and to dynamically choose the right amount of punishment and sanction to impose on them ( Dynamic Adaptation Heuristic ). The results obtained through agent-based simulation show us that sanction is more effective and less costly than punishment in the achievement and maintenance of cooperation and it makes the population more resilient to sudden changes than if it were enforced only by mere punishment.

Human environments are challenging for robots, which need to be trainable by lay people and learn new behaviours rapidly without disrupting much the ongoing activity. A system that integrates AI techniques for planning and learning is here proposed to satisfy these strong demands. The approach rapidly learns planning operators from few action experiences using a competitive strategy where many alternatives of cause-effect explanations are evaluated in parallel, and the most successful ones are used to generate the operators. The success of a cause-effect explanation is evaluated by a probabilistic estimate that compensates the lack of experience, producing more confident estimations and speeding up the learning in relation to other known estimates. The system operates without task interruption by integrating in the planning-learning loop a human teacher that supports the planner in making decisions. All the mechanisms are integrated and synchronized in the robot using a general decision-making framework. The feasibility and scalability of the architecture are evaluated in two different robot platforms: a Stäubli arm, and the humanoid ARMAR III.

Decentralized partially observable Markov decision processes (DEC-POMDPs) are used to plan policies for multiple agents that must maximize a joint reward function but do not communicate with each other. The agents act under uncertainty about each other and the environment. This planning task arises in optimization of wireless networks, and other scenarios where communication between agents is restricted by costs or physical limits. DEC-POMDPs are a promising solution, but optimizing policies quickly becomes computationally intractable when problem size grows. Factored DEC-POMDPs allow large problems to be described in compact form, but have the same worst case complexity as non-factored DEC-POMDPs. We propose an efficient optimization algorithm for large factored infinite-horizon DEC-POMDPs. We formulate expectation-maximization based optimization into a new form, where complexity can be kept tractable by factored approximations. Our method performs well, and it can solve problems with more agents and larger state spaces than state of the art DEC-POMDP methods. We give results for factored infinite-horizon DEC-POMDP problems with up to 10 agents.

The problem of grasping is widely studied in the The problem of semantic part decomposition is still an robotics community. This project focuses on the open problem and, to the best of our knowledge, there are identification of object graspable features using images no tools available to automatically create a fuzzy ontology and object structural information. The primary from raw data taken from an image. The use of fuzzy DLs for aim is the creation of a framework in which the information object recognition has been investigated in some works such gathered by the vision system can be integrated as [Hudelot et al., 2008], in which little advantage is taken with automatically generated knowledge, from the (partial) fuzzy extension and from the expressivity modelled by means of fuzzy description logics. of the used logic (i.e., no cardinality restrictions are used); furthermore, a preliminary phase of semantic annotation of the images by domain experts has to be performed.