Costly preference elicitation has also been studied The last two decades have seen a growing interest in the setting of auctions; notably by Conen and Sandholm in the development of automated agents that are [2001] and Parkes [2005]. These works are primarily able to negotiate on the user's behalf. When representing aimed at designing mechanisms that can avoid unnecessary a user in a negotiation, it is essential for the elicitation. Costly preference elicitation may alternatively be agent to understand the user's preferences, without cast as a problem in which agents have to allocate costly computational exposing them to elicitation fatigue. To this end, we resources to compute their valuation [Larson and propose a new model in which a negotiating agent Sandholm, 2001], but this work focuses on interactions between may incrementally elicit the user's preference during different strategies.

Probabilistic sentential decision diagrams (PSDDs) are a tractable representation of structured probability spaces, which are characterized by complex logical constraints on what constitutes a possible world. We develop general-purpose techniques for probabilistic reasoning and learning with PSDDs, allowing one to compute the probabilities of arbitrary logical formulas and to learn PSDDs from incomplete data. We illustrate the effectiveness of these techniques in the context of learning preference distributions, to which considerable work has been devoted in the past. We show, analytically and empirically, that our proposed framework is general enough to support diverse and complex data and query types. In particular, we show that it can learn maximum-likelihood models from partial rankings, pairwise preferences, and arbitrary preference constraints. Moreover, we show that it can efficiently answer many queries exactly, from expected and most likely rankings, to the probability of pairwise preferences, and diversified recommendations. This case study illustrates the effectiveness and flexibility of the developed PSDD framework as a domain-independent tool for learning and reasoning with structured probability spaces.

Whereas previous work on non-deterministic planning has focused on characterizing (and computing) "loopy" but "closed" plans, we look here at the kind of environments that these plans are to be executed in. In particular, we provide a logical characterization of the standard "fairness'' assumption used, and show that strong cyclic plans are correct solution concepts for fair environments.  We argue then that such logical characterization allows us to recast non-deterministic planning as a reactive synthesis task, and show that for a special case, recent efficient synthesis techniques can be applied.

The integration of the various specialized components of cognitive systems poses a challenge, in particular for those architectures that combine planning, inference, and human-computer interaction (HCI). An approach is presented that exploits a single source of common knowledge contained in an ontology. Based upon the knowledge contained in it, specialized domain models for the cognitive systems' components can be generated automatically. Our integration targets planning in the form of hierarchical planning, being well-suited for HCI as it mimics planning done by humans. We show how the hierarchical structures of such planning domains can be (partially) inferred from declarative background knowledge. The same ontology furnishes the structure of the interaction between the cognitive system and the user. First, explanations of plans presented to users are enhanced by ontology explanations. Second, a dialog domain is created from the ontology coherent with the planning domain. We demonstrate the application of our technique in a fitness training scenario.

In this paper, we study the expressive power of first-order disjunctive logic programming (DLP) and normal logic programming (NLP) under the stable model semantics. We show that, unlike the propositional case, first-order DLP is strictly more expressive than NLP. This result still holds even if auxiliary predicates are allowed, assuming that NP not equals to coNP. On the other side, we propose a partial translation from first-order DLP to NLP via unfolding and shifting, which suggests a sound yet incomplete approach to implement DLP via NLP solvers. We also identify some NLP definable subclasses, and conjecture to exactly capture NLP definability by unfolding and shifting.

Pareto optimization solves a constrained optimization task by reformulating the task as a bi-objective problem. Pareto optimization has been shown quite effective in applications; however, it has little theoretical support. This work theoretically compares Pareto optimization with a penalty approach, which is a common method transforming a constrained optimization into an unconstrained optimization. We prove that on two large classes of constrained Boolean optimization problems, minimum matroid optimization (P-solvable) and minimum cost coverage (NP-hard), Pareto optimization is more efficient than the penalty function method for obtaining the optimal and approximate solutions, respectively. Furthermore, on a minimum cost coverage instance, we also show the advantage of Pareto optimization over a greedy algorithm.

In repeated stochastic games (RSGs), an agent must quickly adapt to the behavior of previously unknown associates, who may themselves be learning. This machine-learning problem is particularly challenging due, in part, to the presence of multiple (even infinite) equilibria and inherently large strategy spaces. In this paper, we introduce a method to reduce the strategy space of two-player general-sum RSGs to a handful of expert strategies. This process, called mega, effectually reduces an RSG to a bandit problem. We show that the resulting strategy space preserves several important properties of the original RSG, thus enabling a learner to produce robust strategies within a reasonably small number of interactions. To better establish strengths and weaknesses of this approach, we empirically evaluate the resulting learning system against other algorithms in three different RSGs.

The need for diversification manifests in various recommendation use cases. In this work, we propose a novel approach to diversifying a list of recommended items, which maximizes the utility of the items subject to the increase in their diversity. From a technical perspective, the problem can be viewed as maximization of a modular function on the polytope of a submodular function, which can be solved optimally by a greedy method. We evaluate our approach in an offline analysis, which incorporates a number of baselines and metrics, and in two online user studies. In all the experiments, our method outperforms the baseline methods.

Solving cooperative path finding (CPF) by translating it to propositional satisfiability represents a viable option in highly constrained situations. The task in CPF is to relocate agents from their initial positions to given goals in a collision free manner. In this paper, we propose a reduced time expansion that is focused on makespan sub-optimal solving. The suggested reduced time expansion is especially beneficial in conjunction with a goal decomposition where agents are relocated one by one.

Approximation fixpoint theory (AFT) is an algebraical study of fixpoints of lattice operators. Recently, AFT was extended with the notion of a grounded fixpoint. This type of fixpoint formalises common intuitions from various application domains of AFT, including logic programming, default logic, autoepistemic logic and abstract argumentation frameworks. The study of groundedness was limited to exact lattice points; in this paper, we extend it to the bilattice: for an approximator A of O, we define A-groundedness.  We show that all partial A-stable fixpoints are A-grounded and that the A-well-founded fixpoint is uniquely characterised as the least precise A-grounded fixpoint.  We apply our theory to logic programming and study complexity.