We converted the recently developed BabyAI grid world platform to a sender/receiver setup in order to test the hypothesis that established deep reinforcement learning techniques are sufficient to incentivize the emergence of a grounded discrete communication protocol between general agents. This is in contrast to previous experiments that employed straight-through estimation or tailored inductive biases. Our results show that these can indeed be avoided, by instead providing proper environmental incentives. Moreover, they show that a longer interval between communications in-centivized more abstract semantics. In some cases, the communicating agents adapted to new environments more quickly than monolithic agents, showcasing the potential of emergent discrete communication for transfer learning.

However, even to learn to solve simple tasks it can require millions of interactions. A promising approach to improve the learning speed relies on the options framework [6] An option is a'chunk of behaviour' that is formally defined as an initiation set, establishing in which states the option is available; a policy, indicating which actions to perform in each state; and a termination condition, establishing when the option execution is terminated. RL systems can benefit from the use of options to support faster exploration and learning especially when rewards are sparse or when the solution to a problem involves recurring behaviours. An important open problem is how can an agent autonomously learn options that are useful to solve tasks drawn from a given task distribution. Recent approaches have searched options for specific optimisation problems but they have not studied how optimal options are affected by different task features such as limited learning time budgets, task rewards, initial states, and the learning algorithm used.

One of the main reasons why RL has worked so well in these applications is that we are able simulate millions of interactions with the environment in a relatively short period of time, allowing the agent to experience a large number of different situations in the environment and learn the consequences of its actions. In many real world applications, however, where the agent interacts with the physical world, it might not be easy to generate such a large number of interactions. The time and cost associated with training such systems could render RL an unfeasible approach for training in large scale. As a concrete example, consider training a large number of humanoid robots (agents) to move quickly, as in the Robocup competition [ Farchy et al., 2013 ] . Although the agents have similar dynamics, subtle variations mean that a single policy shared across all agents would not be an effective solution.

Cameras with artificial intelligence (AI) software that the South Korean government claims can detect the likelihood of crime will be installed in Seoul within the year. The Seocho District of South Korea's capital and Electronics and Telecommunications Research Institute (ERTI), a national research institute, said they will install 3,000 cameras at the district by July. The cameras will use AI software that processes the location, time, and behaviour patterns of passersby to measure the likelihood of a crime taking place. The cameras will automatically measure whether somebody is walking normally or tailing someone. It will also detect what passersby are wearing -- such as hats, masks, or glasses -- and what they are carrying with them such as bags or dangerous objects that have a strong possibility of being used to commit a crime.

On the tray is an assortment of shapes: Some cubes, others spheres. The shapes are made from a variety of different materials and represent an assortment of sizes. In total there are, perhaps, eight objects. My question: "Looking at the objects, are there an equal number of large things and metal spheres?" The fact that it sounds as if it is is proof positive of just how simple it actually is.

TEHRAN – Black-clad mourners packed Iran's second city Mashhad on Sunday as the remains of top Gen. Qassem Soleimani were paraded through the streets after he was killed in a US strike. "Iran's wearing black, revenge, revenge," they chanted as darkness fell and they followed a truck carrying Soleimani's coffin towards the floodlit Imam Reza shrine. The mourners threw scarves onto the roof of the truck so that they could be blessed by the "blood of the martyr. Soleimani, who spearheaded Iran's Middle East operations as commander of the Revolutionary Guards' Quds Force, was killed in a U.S. drone strike Friday near Baghdad airport. The attack was ordered by President Donald Trump, who said the Quds commander had been planning an "imminent" attack on U.S. diplomats and forces in Iraq. Soleimani's remains had been returned before dawn to the southwestern city of Ahvaz, where the air resonated with Shiite chants and shouts of "Death to America" during a procession. People held aloft portraits of Soleimani, one of the country's most popular public figures, who is seen as a hero of the 1980-88 Iran-Iraq war. The "million-man" turnout in Mashhad, northeastern Iran, forced the cancellation of a Sunday night ceremony in Tehran, said the Islamic Revolutionary Guard Corps, who urged citizens instead to attend a memorial Monday at Tehran University. In the face of growing Iraqi anger over the strike, the country's parliament Sunday urged the government to oust the roughly 5,200 American troops in Iraq. Soleimani's assassination ratcheted up tensions between arch-enemies Tehran and Washington and sparked fears of a new Middle East war. Iran's supreme leader, Ayatollah Ali Khamenei, vowed "severe revenge" and declared three days of mourning. Late Saturday Trump warned that America would target 52 sites "important to Iran & Iranian culture" and hit them "very fast and very hard" if American personnel or assets were attacked. Iranian Foreign Minister Mohammad Javad Zarif tweeted that "targeting cultural sites is a WAR CRIME.

It's hard to find a tech company that isn't attempting some sort of AI-related product, service, or initiative these days, but eBay went all-in by building its own AI platform, called Krylov. Sanjeev Katariya, eBay's VP and chief architect of AI and platforms, described Krylov in an interview with VentureBeat: "At the very highest level, Krylov is a machine learning platform that enables data scientists and machine learning engineers to ship all different kinds of models for all kinds of data quickly into production, which gets integrated into user experiences that eBay ships globally." It's a multi-tenant, cloud-based platform that involves technologies like computer vision and natural language processing (NLP), techniques including distributed training and hyper-parameter tuning, and tools germane to eBay's services, like merchandising recommendations, buyer personalization, seller price guidance, and shipping estimates. Even if they did, the hard costs -- however significant they may or may not be -- wouldn't fully capture what eBay has invested to build the platform over years of internal organizational efforts around the globe. And after all that, eBay is now open-sourcing Krylov.

If you can't see the YouTube player above, try watching here instead. Baidu has released its annual ranking of the hottest search terms in technology for 2019. Artificial intelligence (AI) garnered more searches than any other tech phrase. "AI is going to open a new chapter of the society of the world that people try to understand ourselves better, rather than the outside world," said Alibaba founder Jack Ma in a discussion with Tesla CEO Elon Musk at the World Artificial Intelligence Conference in Shanghai in August. China issued a plan for next-generation AI in 2017, pledging to turn the industry into a new growth engine.

Health products powered by artificial intelligence are streaming into our lives, from virtual doctor apps to wearable sensors and drugstore chatbots. IBM boasted that its AI could "outthink cancer." Others say computer systems that read X-rays will make radiologists obsolete. AI can help doctors interpret MRIs of the heart, CT scans of the head and photographs of the back of the eye, and could potentially take over many mundane medical chores, freeing doctors to spend more time talking to patients, said Dr. Eric Topol, a cardiologist and executive vice president of Scripps Research in La Jolla. "There's nothing that I've seen in my 30-plus years studying medicine that could be as impactful and transformative" as AI, Topol said. Even the Food and Drug Administration ― which has approved more than 40 AI products in the last five years ― says "the potential of digital health is nothing short of revolutionary."

A series of new features appear to be on the way for Microsoft's AirSim, a robotics and AI simulation platform. The Unreal Engine-based simulator will be adapted to better suit Game of Drones, which pits quadcopter drone racing AI systems against each other in an AirSim simulation. Game of Drones is in its first year, and today Microsoft said it plans to keep the competition open after a winner is named next week. Game of Drones requires AI that can carry out trajectory planning, computer vision, and opponent drone avoidance. Microsoft brought AirSim to the Unity game engine last year.