This article contains summaries of the five symposia that were conducted: (1) Control of the Physical World by Intelligent Agents, (2) Improving Instruction of Introductory AI, (3) Knowledge Representation for Natural Language Processing in Implemented Systems, (4) Planning and Learning: On to Real Applications, and (5) Relevance. Proceedings of most of the symposia are available as technical reports from AAAI. Control of the physical world, whether by mobile robots or by chemical process controllers, involves many disciplines, including conventional process control, neural networks, fuzzy logic, decision theory, planning, and vision. This workshop brought together researchers from these and other fields with the aim of enumerating the methods available; making a stab at generating a framework for putting them together; and addressing questions such as, How can control help AI? and How can AI help control? A recurring theme was the benefits--or lack thereof--of hierarchical systems: A majority of the attendees supported the position that hierarchy was necessary: Low-level subsystems process sensory input and execute control strategies, and higher-level systems select control strategies appropriate for the task at hand, especially by planning and, perhaps, developing and using maps of the environment.

Some of the participants characterized the workshop as "very intense" and "very productive" but pointed out the conviviality of the gathering and the pleasantness of the warm sun, miles of view, and the gentle sea breezes. In response to requests from several participants, nearly half the time available was scheduled for open roundtable discussions. Presentations were limited to I3 thirty-minute talks. A short after-dinner session was held on Tuesday to establish topics for the roundtables. Two themes initially brought up were echoed throughout the rest of the workshop: (1) What are issues and concepts of DA1 that distinguish it from AI and distributed computing?

The 198.5 Workshop on Distxibuted Artificial Intelligence (DAI) was held at Sea Ranch, California, 3 to 6 December 1985. Twentyeight participants gathered in this rugged, windswept northern California coastal village to debate the theory and practice of DAL In content, the 1985 meeting differed from prior meetings (reports on prior DAI workshops can be found in Davis 1980, 1982; Fehling and Erman 1983; and Smith 1985). First, there has been a clear movement beyond the early, classical large-grained DA1 implementation "successes": HEARSAY, the contract net system, the University of Massachusetts (UMASS) distributed vehicle monitoring test bed, and the Rand Corporation air traffic control (ATCJ and remotely piloted vehicles (RPV) studies. The earlier work introduced several problem-solving architectures--the contract-net negotiation framework, the blackboard-based distributed HEARSAY framework, and the hierarchical versus anarchic control regimes developed at Rand, for example--and developed principles for cooperation and organization. New experimental research is refining these architectures and control strategies and providing frameworks for integrating heterogeneous strategies.

Cast your mind back to April, and the image of a United passenger being ejected from an overbooked plane, wrestled to the ground by security guards and then forcibly dragged, kicking and screaming, from the flight he was about to take home. Such an unsavoury incident was deeply damaging for the United brand, but it also cast a shadow over the customer service profession as a whole. How could an established business like United misread a situation so badly? Had the humanity of customer service become so far-removed that rigid procedure replaced common sense? In many ways, 2017 has been a year defined by the customer service profession questioning its own humanity. The proliferation of chatbots, artificial intelligence and voice assistants has increasingly raised the question of where humans fit into the service function in their business.

We always keep hearing that robots or machines will replace human, and our workplaces will change dramatically. The fundamental truth is that it will, and we have an opportunity to start planning for that, but, like anything else, it's unclear exactly when the tipping point will be. Artificial Intelligence is one of the most trending topics in today's date. It is the way of enabling a computer software to think intelligently in a manner similar to that of humans. In technical terms, it is an integrated solution of Machine Learning, Data Science, Data Mining, Predictive Analytics, Multi-agent Systems, and fast & reliable computation.

Before an agent takes an action, it observes the communications from other agents from the previous time step as well as the locations of all entities and objects in the world. It stores that communication in a private recurrent neural network, giving it a memory for the words it hears. We use discrete communication actions (messages formed of separate, word-like symbols) sent over a differentiable communication channel. A communication channel is differentiable if it allows agents to directly inform each other about what message they should have sent at each time step, by slightly altering their messages to make a positive change in the reward both agents expect to receive. Agents accomplish this by calculating the gradient of future reward with respect to changes in the sent messages (i.e.

When Gilbert Serrano opened the door of his potential dream house, a modern, two-bedroom rental, he was surprised to be greeted not by a real estate agent, but by a robot. An iPad mounted on the machine displayed an agent's smiling face. These robots, rolled out last summer in the Bay Area by high-tech property management startup Zenplace, are intended to take the hassle out of coordinating showing times between agents and prospective renters. They're just one piece of the new wave of technology that's changing the way houses are bought, sold and rented, as platforms such as Zillow, Redfin and a host of smaller startups have eroded the real estate agent's importance. These days, clients can use artificial intelligence to comb property data without a human real estate agent, take virtual tours of promising houses from their couches, and even apply for their favorite apartments online.

We study the cost sharing problem for cooperative games in situations where the cost function C is not available via oracle queries, but must instead be learned from samples drawn from a distribution, represented as tuples (S, C(S)), for different subsets S of players. We formalize this approach, which we call statistical cost sharing, and consider the computation of the core and the Shapley value. Expanding on the work by Balcan et al, we give precise sample complexity bounds for computing cost shares that satisfy the core property with high probability for any function with a non-empty core. For the Shapley value, which has never been studied in this setting, we show that for submodular cost functions with curvature bounded curvature kappa it can be approximated from samples from the uniform distribution to a sqrt{1 - kappa} factor, and that the bound is tight. We then define statistical analogues of the Shapley axioms, and derive a notion of statistical Shapley value and that these can be approximated arbitrarily well from samples from any distribution and for any function.

We consider a two-player sequential game in which agents have the same reward function but may disagree on the transition probabilities of an underlying Markovian model of the world. By committing to play a specific policy, the agent with the correct model can steer the behavior of the other agent, and seek to improve utility. We model this setting as a multi-view decision process, which we use to formally analyze the positive effect of steering policies. Furthermore, we develop an algorithm for computing the agents' achievable joint policy, and we experimentally show that it can lead to a large utility increase when the agents' models diverge.

We study online reinforcement learning in average-reward stochastic games (SGs). An SG models a two-player zero-sum game in a Markov environment, where state transitions and one-step payoffs are determined simultaneously by a learner and an adversary. We propose the \textsc{UCSG} algorithm that achieves a sublinear regret compared to the game value when competing with an arbitrary opponent. This result improves previous ones under the same setting. The regret bound has a dependency on the \textit{diameter}, which is an intrinsic value related to the mixing property of SGs. Slightly extended, \textsc{UCSG} finds an $\varepsilon$-maximin stationary policy with a sample complexity of $\tilde{\mathcal{O}}\left(\text{poly}(1/\varepsilon)\right)$, where $\varepsilon$ is the error parameter. To the best of our knowledge, this extended result is the first in the average-reward setting. In the analysis, we develop Markov chain's perturbation bounds for mean first passage times and techniques to deal with non-stationary opponents, which may be of interest in their own right.