Control of the air in envisioned large-scale battles against near-peer adversaries will require revolutionary new approaches to airborne mission management, where decision authority and platform autonomy are dynamically delegated and functional roles and combat capabilities are assigned across multiple distributed tiers of platforms and human operators. System capabilities range from traditional airborne battle managers, to manned tactical aviators, to autonomous unmanned aerial systems. Due to the overwhelming complexity, human operators will require the assistance of advanced autonomy decision aids with new mechanisms for operator supervision and management of teams of manned and unmanned systems. In this paper we describe a conceptual distributed mission management approach that employs novel human-automation teaming constructs to address the complexity of envisioned operations in highly contested environments. We then discuss a cognitive engineering approach to designing roleand task-tailored human machine interfaces between humans and the autonomous systems. We conclude with a discussion of multi-level evaluation approaches for experimentation.

Datasets with hundreds to tens of thousands features is the new norm. Feature selection constitutes a central problem in machine learning, where the aim is to derive a representative set of features from which to construct a classification (or prediction) model for a specific task. Our experimental study involves microarray gene expression datasets; these are high-dimensional and noisy datasets that contain genetic data typically used for distinguishing between benign or malicious tissues or classifying different types of cancer. In this paper, we formulate feature selection as a multiagent coordination problem and propose a novel feature selection method using multiagent reinforcement learning. The central idea of the proposed approach is to "assign" a reinforcement learning agent to each feature where each agent learns to control a single feature; we refer to this approach as MARL. Applying this to microarray datasets creates an enormous multiagent coordination problem between thousands of learning agents. To address the scalability challenge we apply a form of reward shaping called CLEAN rewards. We compare in total nine feature selection methods, including state-of-the-art methods, and show that the proposed method using CLEAN rewards can significantly scale-up, thus outperforming the rest of learning-based methods. We further show that a hybrid variant of MARL achieves the best overall performance.

Despite the advances made in artificial intelligence, software agents, and robotics, there is little we see today that we can truly call a fully autonomous system. We conjecture that the main inhibitor for advancing autonomy is lack of trust. Trusted autonomy is the scientific and engineering field to establish the foundations and ground work for developing trusted autonomous systems (robotics and software agents) that can be used in our daily life, and can be integrated with humans seamlessly, naturally and efficiently. In this paper, we review this literature to reveal opportunities for researchers and practitioners to work on topics that can create a leap forward in advancing the field of trusted autonomy. We focus the paper on the `trust' component as the uniting technology between humans and machines. Our inquiry into this topic revolves around three sub-topics: (1) reviewing and positioning the trust modelling literature for the purpose of trusted autonomy; (2) reviewing a critical subset of sensor technologies that allow a machine to sense human states; and (3) distilling some critical questions for advancing the field of trusted autonomy. The inquiry is augmented with conceptual models that we propose along the way by recompiling and reshaping the literature into forms that enables trusted autonomous systems to become a reality. The paper offers a vision for a Trusted Cyborg Swarm, an extension of our previous Cognitive Cyber Symbiosis concept, whereby humans and machines meld together in a harmonious, seamless, and coordinated manner.

We develop a new approach that computes approximate equilibrium strategies in Jotto, a popular word game. Jotto is an extremely large two-player game of imperfect information; its game tree has many orders of magnitude more states than games previously studied, including no-limit Texas hold 'em. To address the fact that the game is so large, we propose a novel strategy representation called oracular form, in which we do not explicitly represent a strategy, but rather appeal to an oracle that quickly outputs a sample move from the strategy's distribution. Our overall approach is based on an extension of the fictitious play algorithm to this oracular setting. We demonstrate the superiority of our computed strategies over the strategies computed by a benchmark algorithm, both in terms of head-to-head and worst-case performance.

A promising direction in computational social choice is to address research problems using computer-aided proving techniques. In particular with SAT solvers, this approach has been shown to be viable not only for proving classic impossibility theorems such as Arrow's Theorem but also for finding new impossibilities in the context of preference extensions. In this paper, we demonstrate that these computer-aided techniques can also be applied to improve our understanding of strategyproof irresolute social choice functions. These functions, however, requires a more evolved encoding as otherwise the search space rapidly becomes much too large. Our contribution is two-fold: We present an efficient encoding for translating such problems to SAT and leverage this encoding to prove new results about strategyproofness with respect to Kelly's and Fishburn's preference extensions. For example, we show that no Pareto-optimal majoritarian social choice function satisfies Fishburn-strategyproofness. Furthermore, we explain how human-readable proofs of such results can be extracted from minimal unsatisfiable cores of the corresponding SAT formulas.

There is a long history in game theory on the topic of Bayesian or "rational" learning, in which each player maintains beliefs over a set of alternative behaviours, or types, for the other players. This idea has gained increasing interest in the artificial intelligence (AI) community, where it is used as a method to control a single agent in a system composed of multiple agents with unknown behaviours. The idea is to hypothesise a set of types, each specifying a possible behaviour for the other agents, and to plan our own actions with respect to those types which we believe are most likely, given the observed actions of the agents. The game theory literature studies this idea primarily in the context of equilibrium attainment. In contrast, many AI applications have a focus on task completion and payoff maximisation. With this perspective in mind, we identify and address a spectrum of questions pertaining to belief and truth in hypothesised types. We formulate three basic ways to incorporate evidence into posterior beliefs and show when the resulting beliefs are correct, and when they may fail to be correct. Moreover, we demonstrate that prior beliefs can have a significant impact on our ability to maximise payoffs in the long-term, and that they can be computed automatically with consistent performance effects. Furthermore, we analyse the conditions under which we are able complete our task optimally, despite inaccuracies in the hypothesised types. Finally, we show how the correctness of hypothesised types can be ascertained during the interaction via an automated statistical analysis.

Condorcet winning sets are a set-valued generalization of the well-known concept of a Condorcet winner. As supersets of Condorcet winning sets are always Condorcet winning sets themselves, an interesting property of preference profiles is the size of the smallest Condorcet winning set they admit. This smallest size is called the Condorcet dimension of a preference profile. Since little is known about profiles that have a certain Condorcet dimension, we show in this paper how the problem of finding a preference profile that has a given Condorcet dimension can be encoded as a satisfiability problem and solved by a SAT solver. Initial results include a minimal example of a preference profile of Condorcet dimension 3, improving previously known examples both in terms of the number of agents as well as alternatives. Due to the high complexity of such problems it remains open whether a preference profile of Condorcet dimension 4 exists.

A machine capable of performing complex tasks without requiring laborious programming would be tremendously useful in almost any human endeavor, from performing menial jobs for us to helping the advancement of basic and applied research. Given the current availability of powerful hardware and large amounts of machine-readable data, as well as the widespread interest in sophisticated machine learning methods, the times should be ripe for the development of intelligent machines. Still, since "solving AI" seems too complex a task to be pursued all at once, in the last decades the computational community has preferred to focus on solving relatively narrow empirical problems that are important for specific applications, but do not address the overarching goal of developing general-purpose intelligent machines. In this article, we propose an alternative approach: we first define the general characteristics we think intelligent machines should possess, and then we present a concrete roadmap to develop them in realistic, small steps, that are however incrementally structured in such a way that, jointly, they should lead us close to the ultimate goal of implementing a powerful AI. The article is organized as follows.

Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal, approach. Most non-trivial models thus require the adjustment of several to many learning parameters, which is often done on a case-by-case basis by an external party. Meta-learning refers to the ability of an agent to autonomously and dynamically adjust its own learning parameters, or meta-parameters. In this work we show how projective simulation, a recently developed model of artificial intelligence, can naturally be extended to account for meta-learning in reinforcement learning settings. The projective simulation approach is based on a random walk process over a network of clips. The suggested meta-learning scheme builds upon the same design and employs clip networks to monitor the agent's performance and to adjust its meta-parameters "on the fly". We distinguish between "reflexive adaptation" and "adaptation through learning", and show the utility of both approaches. In addition, a trade-off between flexibility and learning-time is addressed. The extended model is examined on three different kinds of reinforcement learning tasks, in which the agent has different optimal values of the meta-parameters, and is shown to perform well, reaching near-optimal to optimal success rates in all of them, without ever needing to manually adjust any meta-parameter.

Studies on computational neuroscience through functional magnetic resonance imaging (fMRI) and following biological inspired system stated that human action recognition in the brain of mammalian leads two distinct pathways in the model, which are specialized for analysis of motion (optic flow) and form information. Principally, we have defined a novel and robust form features applying active basis model as form extractor in form pathway in the biological inspired model. An unbalanced synergetic neural net-work classifies shapes and structures of human objects along with tuning its attention parameter by quantum particle swarm optimization (QPSO) via initiation of Centroidal Voronoi Tessellations. These tools utilized and justified as strong tools for following biological system model in form pathway. But the final decision has done by combination of ultimate outcomes of both pathways via fuzzy inference which increases novality of proposed model. Combination of these two brain pathways is done by considering each feature sets in Gaussian membership functions with fuzzy product inference method. Two configurations have been proposed for form pathway: applying multi-prototype human action templates using two time synergetic neural network for obtaining uniform template regarding each actions, and second scenario that it uses abstracting human action in four key-frames. Experimental results showed promising accuracy performance on different datasets (KTH and Weizmann).