Computer Science

AI systems often rely on two key components: a specified goal or reward function and an optimization algorithm to compute the optimal behavior for that goal. This approach is intended to provide value for a principal: the user on whose behalf the agent acts. The objectives given to these agents often refer to a partial specification of the principal's goals. We consider the cost of this incompleteness by analyzing a model of a principal and an agent in a resource constrained world where the L attributes of the state correspond to different sources of utility for the principal. We assume that the reward function given to the agent only has support on J<L attributes. The contributions of our paper are as follows: 1) we propose a novel model of an incomplete principal-agent problem from artificial intelligence; 2) we provide necessary and sufficient conditions under which indefinitely optimizing for any incomplete proxy objective leads to arbitrarily low overall utility; and 3) we show how modifying the setup to allow reward functions that reference the full state or allowing the principal to update the proxy objective over time can lead to higher utility solutions. The results in this paper argue that we should view the design of reward functions as an interactive and dynamic process and identifies a theoretical scenario where some degree of interactivity is desirable.

Globally operating enterprises selling large and complex products and services often have to deal with situations where variability models are locally developed to take into account the requirements of local markets. For example, cars sold on the U.S. market are represented by variability models in some or many aspects different from European ones. In order to support global variability management processes, variability models and the underlying knowledge bases often need to be integrated. This is a challenging task since an integrated knowledge base should not produce results which are different from those produced by the individual knowledge bases. In this paper, we introduce an approach to variability model integration that is based on the concepts of contextual modeling and conflict detection. We present the underlying concepts and the results of a corresponding performance analysis.

Problems affecting the transport of people or goods are plentiful in industry and commerce and they also appear to be at the origin of much more complex problems. In recent years, the logistics and transport sector keeps growing supported by technological progress, i.e. companies to be competitive are resorting to innovative technologies aimed at efficiency and effectiveness. This is why companies are increasingly using technologies such as Artificial Intelligence (AI), Blockchain and Internet of Things (IoT). Artificial intelligence, in particular, is often used to solve optimization problems in order to provide users with the most efficient ways to exploit available resources. In this work we present an overview of our current research activities concerning the development of new algorithms, based on CLP techniques, for route planning problems exploiting the geometric information intrinsically present in many of them or in some of their variants. The research so far has focused in particular on the Euclidean Traveling Salesperson Problem (Euclidean TSP) with the aim to exploit the results obtained also to other problems of the same category, such as the Euclidean Vehicle Routing Problem (Euclidean VRP), in the future.

Sampling is a popular method for approximate inference when exact inference is impractical. Generally, sampling algorithms do not exploit context-specific independence (CSI) properties of probability distributions. We introduce context-specific likelihood weighting (CS-LW), a new sampling methodology, which besides exploiting the classical conditional independence properties, also exploits CSI properties. Unlike the standard likelihood weighting, CS-LW is based on partial assignments of random variables and requires fewer samples for convergence due to the sampling variance reduction. Furthermore, the speed of generating samples increases. Our novel notion of contextual assignments theoretically justifies CS-LW. We empirically show that CS-LW is competitive with state-of-the-art algorithms for approximate inference in the presence of a significant amount of CSIs.

Executing a Golog program on an actual robot typically requires additional steps to account for hardware or software details of the robot platform, which can be formulated as constraints on the program. Such constraints are often temporal, refer to metric time, and require modifications to the abstract Golog program. We describe how to formulate such constraints based on a modal variant of the Situation Calculus. These constraints connect the abstract program with the platform models, which we describe using timed automata. We show that for programs over finite domains and with fully known initial state, the problem of synthesizing a controller that satisfies the constraints while preserving the effects of the original program can be reduced to MTL synthesis. We do this by constructing a timed automaton from the abstract program and synthesizing an MTL controller from this automaton, the platform models, and the constraints. We prove that the synthesized controller results in execution traces which are the same as those of the original program, possibly interleaved with platform-dependent actions, that they satisfy all constraints, and that they have the same effects as the traces of the original program. By doing so, we obtain a decidable procedure to synthesize a controller that satisfies the specification while preserving the original program.

Simulations, along with other similar applications like virtual worlds and video games, require computational models of intelligence that generate realistic and credible behavior for the participating synthetic characters. Cognitive architectures, which are models of the fixed structure underlying intelligent behavior in both natural and artificial systems, provide a conceptually valid common basis, as evidenced by the current efforts towards a standard model of the mind, to generate human-like intelligent behavior for these synthetic characters. Sigma is a cognitive architecture and system that strives to combine what has been learned from four decades of independent work on symbolic cognitive architectures, probabilistic graphical models, and more recently neural models, under its graphical architecture hypothesis. Sigma leverages an extended form of factor graphs towards a uniform grand unification of not only traditional cognitive capabilities but also key non-cognitive aspects, creating unique opportunities for the construction of new kinds of cognitive models that possess a Theory-of-Mind and that are perceptual, autonomous, interactive, affective, and adaptive. In this paper, we will introduce Sigma along with its diverse capabilities and then use three distinct proof-of-concept Sigma models to highlight combinations of these capabilities: (1) Distributional reinforcement learning models in; (2) A pair of adaptive and interactive agent models that demonstrate rule-based, probabilistic, and social reasoning; and (3) A knowledge-free exploration model in which an agent leverages only architectural appraisal variables, namely attention and curiosity, to locate an item while building up a map in a Unity environment.

Constraint-based environments such as configuration systems, recommender systems, and scheduling systems support users in different decision making scenarios. These environments exploit a knowledge base for determining solutions of interest for the user. The development and maintenance of such knowledge bases is an extremely time-consuming and error-prone task. Users often specify constraints which do not reflect the real-world. For example, redundant constraints are specified which often increase both, the effort for calculating a solution and efforts related to knowledge base development and maintenance. In this paper we present a new algorithm (CoreDiag) which can be exploited for the determination of minimal cores (minimal non-redundant constraint sets). The algorithm is especially useful for distributed knowledge engineering scenarios where the degree of redundancy can become high. In order to show the applicability of our approach, we present an empirical study conducted with commercial configuration knowledge bases.

Testing and evaluation is a crucial step in the development and deployment of Connected and Automated Vehicles (CAVs). To comprehensively evaluate the performance of CAVs, it is of necessity to test the CAVs in safety-critical scenarios, which rarely happen in naturalistic driving environment. Therefore, how to purposely and systematically generate these corner cases becomes an important problem. Most existing studies focus on generating adversarial examples for perception systems of CAVs, whereas limited efforts have been put on the decision-making systems, which is the highlight of this paper. As the CAVs need to interact with numerous background vehicles (BVs) for a long duration, variables that define the corner cases are usually high dimensional, which makes the generation a challenging problem. In this paper, a unified framework is proposed to generate corner cases for the decision-making systems. To address the challenge brought by high dimensionality, the driving environment is formulated based on Markov Decision Process, and the deep reinforcement learning techniques are applied to learn the behavior policy of BVs. With the learned policy, BVs will behave and interact with the CAVs more aggressively, resulting in more corner cases. To further analyze the generated corner cases, the techniques of feature extraction and clustering are utilized. By selecting representative cases of each cluster and outliers, the valuable corner cases can be identified from all generated corner cases. Simulation results of a highway driving environment show that the proposed methods can effectively generate and identify the valuable corner cases.

The same optimization problem underlies counterfactual explanations (CEs) and adversarial examples (AEs). While this is well known, the relationship between the two at the conceptual level remains unclear. The present paper provides exactly the missing conceptual link. We compare CEs and AEs with respect to their philosophical basis, aims, and modeling techniques. We argue that CEs are a more general object-class than AEs. In particular, we introduce the conceptual distinction between feasible and contesting CEs and show that AEs correspond to the latter.

We present counterfactual planning as a design approach for creating a range of safety mechanisms that can be applied in hypothetical future AI systems which have Artificial General Intelligence. The key step in counterfactual planning is to use an AGI machine learning system to construct a counterfactual world model, designed to be different from the real world the system is in. A counterfactual planning agent determines the action that best maximizes expected utility in this counterfactual planning world, and then performs the same action in the real world. We use counterfactual planning to construct an AGI agent emergency stop button, and a safety interlock that will automatically stop the agent before it undergoes an intelligence explosion. We also construct an agent with an input terminal that can be used by humans to iteratively improve the agent's reward function, where the incentive for the agent to manipulate this improvement process is suppressed. As an example of counterfactual planning in a non-agent AGI system, we construct a counterfactual oracle. As a design approach, counterfactual planning is built around the use of a graphical notation for defining mathematical counterfactuals. This two-diagram notation also provides a compact and readable language for reasoning about the complex types of self-referencing and indirect representation which are typically present inside machine learning agents.