AI agents continue to rack up wins in the video game world. Last week, OpenAI's bots were playing Dota 2; this week, it's Quake III, with a team of researchers from Google's DeepMind subsidiary successfully training agents that can beat humans at a game of capture the flag. As we've seen with previous examples of AI playing video games, the challenge here is training an agent that can navigate a complex 3D environment with imperfect information. DeepMind's researchers used a method of AI training that's also becoming standard: reinforcement learning, which is basically training by trial and error at a huge scale. Agents are given no instructions on how to play the game, but simply compete against themselves until they work out the strategies needed to win. Usually this means one version of the AI agent playing against an identical clone.

Above: four of our trained agents play together on an indoor and outdoor procedurally generated Capture the Flag level. Billions of people inhabit the planet, each with their own individual goals and actions, but still capable of coming together through teams, organisations and societies in impressive displays of collective intelligence. This is a setting we call multi-agent learning: many individual agents must act independently, yet learn to interact and cooperate with other agents. This is an immensely difficult problem - because with co-adapting agents the world is constantly changing. To investigate this problem we look at 3D first-person multiplayer video games.

For Hollywood, AI is a somewhat nuanced boogie-man. Movies like Terminator and She propose a generally intelligent agent capable of being more human than human, at least in certain circumstances. The reality of AI thankfully falls far short. The mundanity of current human/AI interactions doesn't diminish the need for the engineers and designers of these systems to give some thought to human interactions. I recognize this obscures a lot of complexity but it's not really relevant here).

The design of personalized incentives or recommendations to improve user engagement is gaining prominence as digital platform providers continually emerge. We propose a multi-armed bandit framework for matching incentives to users, whose preferences are unknown a priori and evolving dynamically in time, in a resource constrained environment. We design an algorithm that combines ideas from three distinct domains: (i) a greedy matching paradigm, (ii) the upper confidence bound algorithm (UCB) for bandits, and (iii) mixing times from the theory of Markov chains. For this algorithm, we provide theoretical bounds on the regret and demonstrate its performance via both synthetic and realistic (matching supply and demand in a bike-sharing platform) examples.

We study the problem of planning collision-free paths for a group of homogeneous robots. We propose a novel approach for turning the paths that were planned egocentrically by the robots, e.g. without taking other robots' moves into account, into collision-free trajectories and evaluate it empirically. Suggested algorithm is much faster (up to one order of magnitude) than state-of-the-art but this comes at the price of notable drop-down of the solution cost.

The team focused on a capture the flag mode, one in which the map changes from match to match. Its AI agents had to learn general strategies to be able to adapt to each new map, something humans do easily. The agents also needed to both cooperate with team members as well as compete against the opposite team, and be able to adjust to different enemy play styles. "Our agents must learn from scratch how to see, act, cooperate, and compete in unseen environments, all from a single reinforcement signal per match: whether their team won or not," wrote the researchers in a blog post. They trained a population of AI-powered agents that learn by playing the game, much like we do.

Greedy algorithms are known to provide, in polynomial time, near optimal approximation guarantees for Combinatorial Auctions (CAs) with multidimensional bidders. It is known that truthful greedy-like mechanisms for CAs with multi-minded bidders do not achieve good approximation guarantees. In this work, we seek a deeper understanding of greedy mechanism design and investigate under which general assumptions, we can have efficient and truthful greedy mechanisms for CAs. Towards this goal, we use the framework of priority algorithms and weak and strong verification, where the bidders are not allowed to overbid on their winning set or on any subset of this set, respectively. We provide a complete characterization of the power of weak verification showing that it is sufficient and necessary for any greedy fixed priority algorithm to become truthful with the use of money or not, depending on the ordering of the bids. Moreover, we show that strong verification is sufficient and necessary to obtain a 2-approximate truthful mechanism with money, based on a known greedy algorithm, for the problem of submodular CAs in finite bidding domains. Our proof is based on an interesting structural analysis of the strongly connected components of the declaration graph.

Research in AI continues to make video games better. The technology informs NPCs that can move and fight more convincingly, orcs with personalities and ever-more realistic visuals. Now researchers at DeepMind have taught an AI to play a customized version of Quake III Arena like a human. The team focused on a capture the flag mode, one in which the map changes from match to match. Its AI agents had to learn general strategies to be able to adapt to each new map, something humans do easily.

Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games. However, the real-world contains multiple agents, each learning and acting independently to cooperate and compete with other agents, and environments reflecting this degree of complexity remain an open challenge. In this work, we demonstrate for the first time that an agent can achieve human-level in a popular 3D multiplayer first-person video game, Quake III Arena Capture the Flag, using only pixels and game points as input. These results were achieved by a novel two-tier optimisation process in which a population of independent RL agents are trained concurrently from thousands of parallel matches with agents playing in teams together and against each other on randomly generated environments. Each agent in the population learns its own internal reward signal to complement the sparse delayed reward from winning, and selects actions using a novel temporally hierarchical representation that enables the agent to reason at multiple timescales. During game-play, these agents display human-like behaviours such as navigating, following, and defending based on a rich learned representation that is shown to encode high-level game knowledge. In an extensive tournament-style evaluation the trained agents exceeded the win-rate of strong human players both as teammates and opponents, and proved far stronger than existing state-of-the-art agents. These results demonstrate a significant jump in the capabilities of artificial agents, bringing us closer to the goal of human-level intelligence.

Currently, we stand on the brink of a fourth Industrial revolution. Artificial Intelligence or AI is the intelligence demonstrated by machines for performing tasks. It is a specialized section of computer science which focuses on creating intelligent machines that think, react and work like humans. Some of the activities computers with artificial intelligence are built for includes problem solving, learning, analysing, speech recognition, and much more. AI is a vast field in itself, and it encompasses a wide spectrum of technologies such as Machine Learning, Automated Intelligence System, Deep learning, Neural Network, Computational Argumentation, and Multi-agent Systems to solve problems that currently seem impossible.