Policy gradient methods are often applied to reinforcement learning in continuous multiagent games. These methods perform local search in the joint-action space, and as we show, they are susceptable to a game-theoretic pathology known as relative overgeneralization. To resolve this issue, we propose Multiagent Soft Q-learning, which can be seen as the analogue of applying Q-learning to continuous controls. We compare our method to MADDPG, a state-of-the-art approach, and show that our method achieves better coordination in multiagent cooperative tasks, converging to better local optima in the joint action space.

We consider the problem of fairly allocating indivisible goods, among agents, under cardinality constraints and additive valuations. In this setting, we are given a partition of the entire set of goods---i.e., the goods are categorized---and a limit is specified on the number of goods that can be allocated from each category to any agent. The objective here is to find a fair allocation in which the subset of goods assigned to any agent satisfies the given cardinality constraints. This problem naturally captures a number of resource-allocation applications, and is a generalization of the well-studied (unconstrained) fair division problem. The two central notions of fairness, in the context of fair division of indivisible goods, are envy freeness up to one good (EF1) and the (approximate) maximin share guarantee (MMS). We show that the existence and algorithmic guarantees established for these solution concepts in the unconstrained setting can essentially be achieved under cardinality constraints. Specifically, we develop efficient algorithms which compute EF1 and approximately MMS allocations in the constrained setting. Furthermore, focusing on the case wherein all the agents have the same additive valuation, we establish that EF1 locations exist even under matroid constraints.

Flocking is a coordinated collective behavior that results from local sensing between individual agents that have a tendency to orient towards each other. Flocking is common among animal groups and might also be useful in robotic swarms. In the interest of learning how to control flocking behavior, recent work in the multiagent systems literature has explored the use of influencing agents for guiding flocking agents to face a target direction. The existing work in this domain has focused on simulation settings of small areas with toroidal shapes. In such settings, agent density is high, so interactions are common, and flock formation occurs easily. In our work, we study new environments with lower agent density, wherein interactions are more rare. We study the efficacy of placement strategies and influencing agent behaviors drawn from the literature, and find that the behaviors that have been shown to work well in high-density conditions tend to be much less effective in lower density environments. The source of this ineffectiveness is that the influencing agents explored in prior work tended to face directions optimized for maximal influence, but which actually separate the influencing agents from the flock. We find that in low-density conditions maintaining a connection to the flock is more important than rushing to orient towards the desired direction. We use these insights to propose new influencing agent behaviors, which we dub "follow-then-influence"; agents act like normal members of the flock to achieve positions that allow for control and then exert their influence. This strategy overcomes the difficulties posed by low density environments.

"YOUR CALL IS important to us," a recorded voice tells resigned customers as they wait endlessly to speak to a human agent. AI is starting to help companies improve the quality and consistency of their service in order to persuade customers that they do in fact care about them. Ocado, a British online grocer, receives around 10,000 e-mails from customers every day and uses AI to detect the prevailing sentiment in them. It now replies to the most urgent ones first, and is planning to route complaints to agents with expertise in the relevant field. "Like other applications of AI, it's about trying to make humans more efficient, not take them out of the process entirely," says Paul Clarke, Ocado's chief technology officer.

To find solutions to problems commonly used in science and engineering, algorithms are required. An algorithm is a step-by-step computational procedure or a set of rules to be followed by a computer. One of the oldest algorithms is the Euclidean algorithm for finding the greatest common divisor (gcd) of two integers such as 12345 and 125, and this algorithm was first given in detail in Euclid's Elements about 2300 years ago (Chabert 1999). Modern computing involves a large set of different algorithms from fast Fourier transform (FFT) to image processing techniques and from conjugate gradient methods to finite element methods. Optimization problems in particular require specialized optimization techniques, ranging from the simple Newton-Raphson's method to more sophisticated simplex methods for linear programming. Modern trends tend to use a combination of traditional techniques in combination with contemporary stochastic metaheuristic algorithms such as genetic algorithms, firefly algorithm and particle swarm optimization.

The mine detection in an unexplored area is an optimization problem where multiple mines, randomly distributed throughout an area, need to be discovered and disarmed in a minimum amount of time. We propose a strategy to explore an unknown area, using a stigmergy approach based on ants behavior, and a novel swarm based protocol to recruit and coordinate robots for disarming the mines cooperatively. Simulation tests are presented to show the effectiveness of our proposed Ant-based Task Robot Coordination (ATRC) with only the exploration task and with both exploration and recruiting strategies. Multiple minimization objectives have been considered: the robots' recruiting time and the overall area exploration time. We discuss, through simulation, different cases under different network and field conditions, performed by the robots. The results have shown that the proposed decentralized approaches enable the swarm of robots to perform cooperative tasks intelligently without any central control.

Are the U.S., China, and Russia recklessly undertaking an "AI arms race"? Clearly, there is military competition among these great powers to advance a range of applications of robotics, artificial intelligence, and autonomous systems. So far, the U.S. has been leading the way. AI and autonomy are crucial to the Pentagon's Third Offset strategy. Its Algorithmic Warfare Cross-Functional Team, Project Maven, has become a "pathfinder" for this endeavor and has started to deploy algorithms in the fight against ISIS.

I make some basic observations about hard takeoff, value alignment, and coherent extrapolated volition, concepts which have been central in analyses of superintelligent AI systems.

Please register here to get Tyche pre-order notification. The purpose of AIBrain is to augment human intelligence with AI by unifying Problem Solving, Learning, and Memory. The power of our practical AI agent comes from two central components, which are a reasoning engine called AICoRE and a human-like memory called Memory Graph. AICoRE (Adaptive Interactive Cognitive Reasoning Engine) is a cognitive reasoning engine by unifying problem solving and learning. AICoRe fully automates the reasoning process from end to end.

This paper presents a technical approach to robot learning of motor skills which combines active intrinsically motivated learning with imitation learning. Our architecture, called SGIM-D, allows efficient learning of high-dimensional continuous sensorimotor inverse models in robots, and in particular learns distributions of parameterised motor policies that solve a corresponding distribution of parameterised goals/tasks. This is made possible by the technical integration of imitation learning techniques within an algorithm for learning inverse models that relies on active goal babbling. After reviewing social learning and intrinsic motivation approaches to action learning, we describe the general framework of our algorithm, before detailing its architecture. In an experiment where a robot arm has to learn to use a flexible fishing line , we illustrate that SGIM-D efficiently combines the advantages of social learning and intrinsic motivation and benefits from human demonstration properties to learn how to produce varied outcomes in the environment, while developing more precise control policies in large spaces.