Some standardized environments have been designed for partially observable multi-agent cooperation, but we find most current environments are synchronous, whereas real-world agents often have their own action spaces leading to asynchrony. Furthermore, fixed agents number limits the scalability of action space, whereas in reality agents number can change resulting in a flexible action space. In addition, current environments are balanced, which is not always the case in the real world where there may be an ability gap between different parties leading to asymmetry. Finally, current environments tend to have less stochasticity with simple state transitions, whereas real-world environments can be highly stochastic and result in extremely risky. To address this gap, we propose WarGame Challenge (WGC) inspired by the Wargame. WGC is a lightweight, flexible, and easy-to-use environment with a clear framework that can be easily configured by users. Along with the benchmark, we provide MARL baseline algorithms such as QMIX and a toolkit to help algorithms complete performance tests on WGC. Finally, we present baseline experiment results, which demonstrate the challenges of WGC. We think WGC enrichs the partially observable multi-agent cooperation domain and introduces more challenges that better reflect the real-world characteristics. Code is release in http://turingai.ia.ac.cn/data\_center/show/10.

Ride-sharing apps like Uber and Lyft have made the daily commute a less frustrating part of the day for many. Now a crowd-sourced fleet of 14-passenger vehicles acquired by Ford is promising more. "What Chariot and Ford is looking forward to doing in the next couple of years is to actually make [your commute], believe it or not, the best part of your day," said Ali Vahabzadeh, founder and chief executive officer of Chariot Transit Inc., a Y Combinator-backed startup. At South by SouthWest in Austin, TX, Vahabzadeh claimed that Chariot is reinventing mass-transit by crowd-sourcing new routes in undeserved or overcrowded areas. Vahabzadeh told John Furrier (@furrier), host of theCUBE, SiliconANGLE Media's mobile live streaming studio, that Chariot is using Artificial Intelligence and commuter data to finetune rider experiences on-board.

The Consumer Electronics Show, the annual moot of the tech gadget industry, is always on the trippy side. But zoom in on CES's transportation options and it gets downright hallucinatory. Cars with legs, flying taxis, sensors that watch your face while you drive, robot deaths, an Uber for ... cabs. While we recover from Vegas, please be advised that what happened there last week has not stayed there. Also this week: Ford nixes Chariot, its app-based shuttle service; the largest electric vertical takeoff and landing aircraft yet takes flight; and we talk to Seattle's Department of Transportation about why it buried a ramp and then dug it back up again, six years later.

On Thursday, five years after launching and two and half years after being acquired by Ford for a reported $65 million, the app-based shuttle service announced it is rolling to a permanent stop. Transportation technology companies have never been sexier than in the past decade, but this stumble is a potent reminder that creating a profitable transportation business can be far harder than it seems. When Chariot launched in 2014, it joined a wave of Uber-inspired "microtransit" tech companies hoping to disrupt transportation services by providing faster, more efficient options for riders sick of--and underserved by--traditional public transit. Less than half a decade on, most have gone the way of the Hawaiian tree snail. San Francisco-based, elitist-wooing Leap Transit closed up shop just three months after its March 2015 launch, amid a regulatory fight with California.

When we think of ancient Greece we generally imagine ruthless highly-trained warriors or cloth clad philosophers pondering the schematics and perimeters of geometry, geography, architecture and the like. But a new book is about to present them as "skilled forecasters, accurately predicting the rise of artificial intelligence, killer androids and driverless cars." More than 2,500 years ago, Greek mythologists, according to American historian Dr Adrienne Mayor of Stanford University, "envisioned many of the technology trends we grapple with today including Killer androids, driverless technology, GPS and AI-powered helper robots." According to an article about Mayors finding in Greek Reporter, in her forthcoming book Gods and Robots: Myths, Machines, and Ancient Dreams of Technology the creations of Hephaestus, the god of metalworking and an invention in Homer's Iliad, were "predictions of the rise of humanoid robots." Dr Mayor, who according to the Stanford University website is an independent folklorist/historian of science investigating natural knowledge contained in pre-scientific myths and oral traditions, claims Hephaestus crafted'mechanical maid's from gold that were designed to anticipate their master's requests and act on them without instruction, much like modern machine learning software.

Rebalancing is a critical service bottleneck for many transportation services, such as Citi Bike. Citi Bike relies on manual orchestrations of rebalancing bikes between dispatchers and field agents. Motivated by such problem and the lack of smart autonomous solutions in this area, this project explored a new RL architecture called Distributed RL (DiRL) with Transfer Learning (TL) capability. The DiRL solution is adaptive to changing traffic dynamics when keeping bike stock under control at the minimum cost. DiRL achieved a 350% improvement in bike rebalancing autonomously and TL offered a 62.4% performance boost in managing an entire bike network. Lastly, a field trip to the dispatch office of Chariot, a ride-sharing service, provided insights to overcome challenges of deploying an RL solution in the real world.

U.S. Transportation Secy.: Self-driving tech will make roads safer Innovation is underway to rethink one of the biggest headaches we face on a daily basis: getting to work. From crowdsourced shuttle buses to companies offering rides to lure top talent, here are concepts used in some cities that could one day help your morning commute. Some of the largest US companies, including Google, Apple and Facebook, offer shuttles or arranged ride shares to get employees to work. These shuttles often come with free WiFi, and pick up near employees' homes. "It's the dawn of private transportation systems operating under the radar," Ryan Croft, co-founder of TransitScreen, a startup providing real-time transit planning information, told CNN.

Home-grown technology company Smartron and University of Southern California (USC) have collaborated to impart personalised education through the applications of machine learning and wearable technologies. USC's Center for Human Applied Reasoning and the Internet of Things (CHARIOT), along with Smartron, would focus on building the framework for creating an effective, classroom-based system for measuring the cognitive and affective influences on learning using smartphones and a range of sensors. "We are pleased to be the first Indian product brand to partner with USC's CHARIOT to collaborate on creating this new and hugely immersive and personalised learning programme based on IoT," said Mahesh Lingareddy, Founder, Smartron founder, on Friday. Smartron recently unveiled "tronX", a first-of-its-kind intelligent ecosystem that connects a range of devices, sensors and systems to "tronX" core, offering evolving experiences and services. "With our wearables powered by "tronX", we will be able to gather and analyse the data to help create the most effective learning interventions for students who may need it," Lingareddy added in a statement.

A Ford Fusion laden with self-driving sensors does some winter weather testing. Ford Motor is in pole position when it comes to benefiting from the coming age of autonomous vehicles. That's the conclusion of a study released Monday by Navigant Research, which sells its in-depth surveys of energy and transportation markets to suppliers, policymakers and other industry stakeholders. The Dearborn-based automaker took the top spot by demonstrating that it has the strategic vision and execution capabilities to both develop automated driving systems as well as deploy them across a range of mobility platforms. Many automakers are targeting 2021 for a roll-out of autonomous vehicles that likely will be part of a ride-sharing network.

A Ford Fusion laden with self-driving sensors does some winter weather testing. Ford Motor is in pole position when it comes to benefiting from the coming age of autonomous vehicles. That's the conclusion of a study released Monday by Navigant Research, which sells its in-depth surveys of energy and transportation markets to suppliers, policymakers and other industry stakeholders. The Dearborn-based automaker took the top spot by demonstrating that it has the strategic vision and execution capabilities to both develop automated driving systems as well as deploy them across a range of mobility platforms. Many automakers are targeting 2021 for a roll-out of AVs that likely will be part of a ride-sharing network.