There is a growing recognition that artists use valuable ways to understand and work with cognitive and perceptual mechanisms to convey desired experiences and narrative in their created artworks (DiPaola et al., 2010; Zeki, 2001). This paper documents our attempt to computationally model the creative process of a portrait painter, who relies on understanding human traits (i.e., personality and emotions) to inform their art. Our system includes an empathic conversational interaction component to capture the dominant personality category of the user and a generative AI Portraiture system that uses this categorization to create a personalized stylization of the user's portrait. This paper includes the description of our systems and the real-time interaction results obtained during the demonstration session of the NeurIPS 2019 Conference.

Modern algorithms in the domain of Deep Reinforcement Learning (DRL) demonstrated remarkable successes; most widely known are those in game-based scenarios, from ATARI video games to Go and the StarCraft~\textsc{II} real-time strategy game. However, applications in the domain of modern Cyber-Physical Systems (CPS) that take advantage a vast variety of DRL algorithms are few. We assume that the benefits would be considerable: Modern CPS have become increasingly complex and evolved beyond traditional methods of modelling and analysis. At the same time, these CPS are confronted with an increasing amount of stochastic inputs, from volatile energy sources in power grids to broad user participation stemming from markets. Approaches of system modelling that use techniques from the domain of Artificial Intelligence (AI) do not focus on analysis and operation. In this paper, we describe the concept of Adversarial Resilience Learning (ARL) that formulates a new approach to complex environment checking and resilient operation: It defines two agent classes, attacker and defender agents. The quintessence of ARL lies in both agents exploring the system and training each other without any domain knowledge. Here, we introduce the ARL software architecture that allows to use a wide range of model-free as well as model-based DRL-based algorithms, and document results of concrete experiment runs on a complex power grid.

Tackling a machine learning problem might feel overwhelming at first. What model to choose?, which architecture might work best? In a process that is mostly driven by trial and error experimentation, those decisions result incredibly important. One aspect that really helps to navigate that universe of decisions is to clearly understand the nature of the problem. In machine learning scenarios, an important part of understanding the problem is based on understanding its environment.

In Markov games, playing against non-stationary opponents with learning ability is still challenging for reinforcement learning (RL) agents, because the opponents can evolve their policies concurrently. This increases the complexity of the learning task and slows down the learning speed of the RL agents. This paper proposes efficient use of rough heuristics to speed up policy learning when playing against concurrent learners. Specifically, we propose an algorithm that can efficiently learn explainable and generalized action selection rules by taking advantages of the representation of quantitative heuristics and an opponent model with an eXtended classifier system (XCS) in zero-sum Markov games. A neural network is used to model the opponent from their behaviors and the corresponding policy is inferred for action selection and rule evolution. In cases of multiple heuristic policies, we introduce the concept of Pareto optimality for action selection. Besides, taking advantages of the condition representation and matching mechanism of XCS, the heuristic policies and the opponent model can provide guidance for situations with similar feature representation. Furthermore, we introduce an accuracy-based eligibility trace mechanism to speed up rule evolution, i.e., classifiers that can match the historical traces are reinforced according to their accuracy. We demonstrate the advantages of the proposed algorithm over several benchmark algorithms in a soccer and a thief-and-hunter scenarios.

An artificial intelligence agent named Tala may open the door on a new way of gathering feedback from New Zealand's Samoan community. The Talanoa Project is a pilot project that uses IBM's artificial intelligence virtual agent solution, Watson, to interact in real time in Samoan for public consultation and community engagement. Developed and designed by Beca, business director Matthew Ensor said it was about consulting with'the silent majority' in the public on projects and community facilities. "We don't hear so much from the people where language is a barrier, where culturally there's no tradition of responding to public consultation. "We then created a conversational agent, it's like a chat-bot and what it does is it mimics the kind of conversation that you would have with a consultation expert," Mr Ensor said. "It will ask open questions about your thoughts on different things and really lets the person lead the conversation rather than a survey form where the questions are completely scripted." Steve O'Donnell from IBM New Zealand's Managing Partner for Global Business Services said this was the first time IBM Watson Assistant had been used for public consultation in New Zealand in a language other than English. "What we are seeing now is AI being able to scale down, and drive value in many industries," he said. "IBM Watson has already transformed the world of customer service, due largely to its ability to understand human sentiment and interact naturally with people and Tala is a promising first step towards that." The Talanoa Project, part funded by Callaghan Innovation, tested Tala among a few dozen Samoan speakers, asking them for their thoughts on their local community facilities. The focus group of Samoans ranged from 19-years of age to 77 being the oldest and included Samoan elders, law students, psychologists and sociologists. "It was overwhelmingly positive the response we got back from the Samoan community," Mr Ensor said. "We had a few people share that it was great to hear technology using their native language.

Such a disappearance is a fundamental consequence not of technology but of human psychology. Whenever people learn something sufficiently well, they cease to be aware of it. Thus, Weiser's vision is even broader: as this technology becomes truly embedded in human activity we won't be aware of it at all. As the field of ubiquitous computing has evolved, with computation embedded in walls, clothes, and so forth, the materiality to support it is often physically and intentionally hidden from the user. Indeed, this material disappearance is often considered evidence of good design. The "agent" metaphor, in particular in its early presentations such as the Knowledge Navigator and Starfire, is also another utopian vision. These virtual agents are typically accessible via peripherals such as screens or phones, doing the bidding of those they serve.

Transferring as fast as possible the functioning of our brain to artificial intelligence is an ambitious goal that would help advance the state of the art in AI and robotics. It is in this perspective that we propose to start from hypotheses derived from an empirical study in a human-robot interaction and to verify if they are validated in the same way for children as for a basic reinforcement learning algorithm. Thus, we check whether receiving help from an expert when solving a simple close-ended task (the Towers of Hano\"i) allows to accelerate or not the learning of this task, depending on whether the intervention is canonical or requested by the player. Our experiences have allowed us to conclude that, whether requested or not, a Q-learning algorithm benefits in the same way from expert help as children do.

Multi-agent learning is a challenging problem in machine learning that has applications in different domains such as distributed control, robotics, and economics. We develop a prescriptive model of multi-agent behavior using Markov games. Since in many multi-agent systems, agents do not necessary select their optimum strategies against other agents (e.g., multi-pedestrian interaction), we focus on models in which the agents play "exploration but near optimum strategies". We model such policies using the Boltzmann-Gibbs distribution. This leads to a set of coupled Bellman equations that describes the behavior of the agents. We introduce a set of conditions under which the set of equations admit a unique solution and propose two algorithms that provably provide the solution in finite and infinite time horizon scenarios. We also study a practical setting in which the interactions can be described using the occupancy measures and propose a simplified Markov game with less complexity. Furthermore, we establish the connection between the Markov games with exploration strategies and the principle of maximum causal entropy for multi-agent systems. Finally, we evaluate the performance of our algorithms via several well-known games from the literature and some games that are designed based on real world applications.

Modeling and simulation is certainly a vast discipline with a broad and complex body of knowledge having, beyond the surface, a large technical and theoretical background (Minsky, 1965) (Banks et al., 2009) (Zeigler et al., 2000) (Boccara, 2003) which consequently, is hard of being completely mastered from modelers coming from disperse domains like biology, ecology or even computer science. Among the existing formalisms, the agent-based or individual-based is increasing gradually the number of adepts in the recent years. The Individual-based modeling is a powerful methodology which is having more and more acceptance between researchers and practitioners of distinct branches from social to biological sciences, including specifically the modeling of ecological processes and microbial consortia studies. Certainly, one of the main reasons for the success of this approach is the relative simplicity for capturing micro-level properties, stochasticity and spatially complex phenomena without the requirement of a high level of mathematical background (Grimm and Railsback, 2005). But the counterpart of the ease for building complex and feature rich models, is the lack of a closed formal mathematical form of the model which implies that the study of these models cannot be attacked analytically.

To avoid the computational requirements of online methods, we can use reinforcement learning (RL) instead. In RL, In recent years, major progress has been made to deploy the agent interacts with a simulation environment many autonomous vehicles and improve safety. However, certain times prior to execution, and at each simulation episode common driving situations like merging in dense traffic are it improves its strategy. The resulting policy can then be still challenging for autonomous vehicles. Situations like deployed online and is often inexpensive to evaluate. RL the one illustrated in Figure 1 often involve negotiating with provides a flexible framework to automatically find good human drivers.