Effective coordination is crucial to solve multi-agent collaborative (MAC) problems. While centralized reinforcement learning methods can optimally solve small MAC instances, they do not scale to large problems and they fail to generalize to scenarios different from those seen during training. In this paper, we consider MAC problems with some intrinsic notion of locality (e.g., geographic proximity) such that interactions between agents and tasks are locally limited. By leveraging this property, we introduce a novel structured prediction approach to assign agents to tasks. At each step, the assignment is obtained by solving a centralized optimization problem (the inference procedure) whose objective function is parameterized by a learned scoring model. We propose different combinations of inference procedures and scoring models able to represent coordination patterns of increasing complexity. The resulting assignment policy can be efficiently learned on small problem instances and readily reused in problems with more agents and tasks (i.e., zero-shot generalization). We report experimental results on a toy search and rescue problem and on several target selection scenarios in StarCraft: Brood War, in which our model significantly outperforms strong rule-based baselines on instances with 5 times more agents and tasks than those seen during training.

Customer queries are the bane of most customer support teams, not because they don't like dealing with them, but because they don't have a proper process in place that lets them handle excessive ticket volumes easily and effectively. When a support ticket drops into a queue, or an agent receives an email with a customer issue, the ticket or email might pass through three different agents before finally landing in the correct hands to deal with the issue – leading to bottlenecks and bad customer experiences. Bugs, forgotten passwords, system errors, integration queries… There are so many different issues that agents have to deal with, so that the customer remains happy and the company retains them. And while customer support endeavors to respond to queries as quickly as possible, it's difficult when faced with huge volumes of tickets. On top of that, more and more customers expect immediate responses – 64% of consumers and 80% of business buyers said they expect companies to respond to and interact with them in real time. Deciding how to tackle customer requests, which to tackle first, and making sure tickets are sent to the right person – or team that's best equipped to deal with the query – are processes that need to run as smoothly as possible, so that organizations can score high on the customer satisfaction scale.

We use artificial intelligence (AI) every day without knowing it. Alexa's speech recognition, Netflix's movie recommendations and Gmail's type-ahead suggestions are all examples of data you share being fed into deep learning AI models to improve your experience. At work, the same technology is increasingly used to deliver smart services -- rooms that book themselves, thermostats that don't cool empty floors and outages that are restored before anyone knows they exist. Achieving Amazon-quality AI with "small data" from your organization is a more complex technical problem. To get enterprise AI right at scale requires thinking differently about how applications and services are deployed and managed.

Security games are an example of a successful real-world application of game theory. The paper defines blameworthiness of the defender and the attacker in security games using the principle of alternative possibilities and provides a sound and complete logical system for reasoning about blameworthiness in such games. Introduction In this paper we study the properties of blameworthiness in security games (von Stackelberg 1934). Security games are used for canine airport patrol (Pita et al. 2008; Jain et al. 2010), airport passenger screening (Brown et al. 2016), protecting endangered animals and fish stocks (Fang, Stone, and Tambe 2015), U.S. Coast Guard port patrol (Sinha et al. 2018; An, Tambe, and Sinha 2016), and randomized deployment of U.S. air marshals (Sinha et al. 2018). Defender \Attacker Terminal 1 Terminal 2 Terminal 1 20 120 Terminal 2 200 16 Figure 1: Expected Human Losses in Security Game G 1. As an example, consider a security game G 1 in which a defender is trying to protect two terminals in an airport from an attacker. Due to limited resources, the defender can patrol only one terminal at a given time. If the defender chooses to patrol Terminal 1 and the attacker chooses to attack Terminal 2, then the human losses at Terminal 2 are estimated at 120, see Figure 1. However, if the defender chooses to patrol Terminal 2 while the attacker still chooses to attack Terminal 2, then the expected number of the human losses at Terminal 2 is only 16, see Figure 1. Generally speaking, the goal of the defender is to minimize human losses, while the goal of the attacker is to maximize them. However, the utility functions in security games usually take into account not only the human losses, but also the cost to protect and to attack the target to the defender and the attacker respectively.

Algorithms, software and smart technologies have a growing presence in cities around the world. Artificial intelligence (AI), agent-based modelling, the internet of things and machine learning can be found practically everywhere now – from lampposts to garbage bins, traffic lights and cars. Not only that, these technologies are also influencing how cities are planned, guiding big decisions about new buildings, transport and infrastructure projects. City-dwellers tend to accept the presence of these technologies passively – if they notice it at all. Yet this acceptance is punctuated by intermittent panic over privacy – take, for example, Transport for London's latest plans to track passenger journeys across the transport network using wifi, which drew criticism from privacy experts.

Researchers from USC and the University of Denver created a simulation in which a three-person team was supported by a virtual agent avatar on screen in a mission that was designed to ensure failure and elicit conflict. The study was designed to look at virtual agents as potential mediators to improve team collaboration during conflict mediation. But in the heat of the moment, will we listen to virtual agents? While some of researchers (Gale Lucas and Jonathan Gratch of the USC Viterbi School Engineering and the USC Institute for Creative Technologies who contributed to this study), had previously found that one-on-one human interactions with a virtual agent therapist yielded more confessions, in this study "Conflict Mediation in Human-Machine Teaming: Using a Virtual Agent to Support Mission Planning and Debriefing," team members were less likely to engage with a male virtual agent named "Chris" when conflict arose. Participating members of the team did not physically accost the device (as we have seen humans attack robots in viral social media posts), but rather were less engaged and less likely to listen to the virtual agent's input once failure ensued and conflict arose among team members. The study was conducted in a military academy environment in which 27 scenarios were engineered to test how the team that included a virtual agent would react to failure and the ensuring conflict.

Generating complex multi-turn goal-oriented dialogue agents is a difficult problem that has seen a considerable focus from many leaders in the tech industry, including IBM, Google, Amazon, and Microsoft. This is in large part due to the rapidly growing market demand for dialogue agents capable of goal-oriented behaviour. Due to the business process nature of these conversations, end-to-end machine learning systems are generally not a viable option, as the generated dialogue agents must be deployable and verifiable on behalf of the businesses authoring them. In this work, we propose a paradigm shift in the creation of goal-oriented complex dialogue systems that dramatically eliminates the need for a designer to manually specify a dialogue tree, which nearly all current systems have to resort to when the interaction pattern falls outside standard patterns such as slot filling. We propose a declarative representation of the dialogue agent to be processed by state-of-the-art planning technology. Our proposed approach covers all aspects of the process; from model solicitation to the execution of the generated plans/dialogue agents. Along the way, we introduce novel planning encodings for declarative dialogue synthesis, a variety of interfaces for working with the specification as a dialogue architect, and a robust executor for generalized contingent plans. We have created prototype implementations of all components, and in this paper, we further demonstrate the resulting system empirically.

P .B. Sujit IIIT Delhi sujit@iiitd.ac.in Abstract --In this paper, we consider a territory guarding game involving pursuers, evaders and a target in an environment that contains obstacles. The goal of the evaders is to capture the target, while that of the pursuers is to capture the evaders before they reach the target. All the agents have limited sensing range and can only detect each other when they are in their observation space. We focus on the challenge of effective cooperation between agents of a team. Finding exact solutions for such multi-agent systems is difficult because of the inherent complexity. We present Multi-Agent Pursuer-Evader Learning (MAPEL), a class of algorithms that use spatiotemporal graph representation to learn structured cooperation. The key concept is that the learning takes place in a decentralized manner and agents use situation report updates to learn about the whole environment from each others' partial observations. We use Recurrent Neural Networks (RNNs) to parameterize the spatiotemporal graph. An agent in MAPEL only updates all the other agents if an opponent or the target is inside its observation space by using situation report. We present a detailed analysis of how these two cooperation methods perform when the number of agents in the game are increased. We provide empirical results to show how agents cooperate under these two methods.

Analyst Forrester defines robotic process automation (RPA) as a technology that provisions software agents – bots – that can mimic human interactions with software systems. These bots run predictable tasks, and act either in concert with humans (attended RPA) or mostly autonomously (unattended RPA). Increasingly, RPA is adding artificial intelligence (AI)-based capabilities, such as reading unstructured data. IT research firm Computer Economics says in its April 2019 Technology trends report that bots are typically taught by human example to respond to various triggers. For example, when an employee submits a change of address form to the human resources (HR) department, the bot could then be used to trigger an update to the records in payroll, benefits systems, expense reporting and accounts payable, just as a human clerical worker might do.

Microsoft is rolling out two new software solutions today to help brick-and-mortar retailers track customers and improve service. Dynamics 365 Connected Store will utilize a combination of computer vision, cameras, and IoT sensors to track customers inside stores and personalize recommendations based on their browsing and buying behavioral data. Events detected by Connected Store will trigger web app notifications or email alerts for in-store staff with predictions to improve sales and store efficiency. Connected Store can do things like sense a need for more staff at checkout counters, identify issues with store equipment, and surface long-term trends for managers. Also new is Dynamics 365 Commerce, software that pulls insights from businesses that have ecommerce and brick-and-mortar retail operations. Dynamics 365 Commerce will also use call center and back office data to power customer personalization.