Tag Archives: come
#435707 AI Agents Startle Researchers With ...
After 25 million games, the AI agents playing hide-and-seek with each other had mastered four basic game strategies. The researchers expected that part.
After a total of 380 million games, the AI players developed strategies that the researchers didn’t know were possible in the game environment—which the researchers had themselves created. That was the part that surprised the team at OpenAI, a research company based in San Francisco.
The AI players learned everything via a machine learning technique known as reinforcement learning. In this learning method, AI agents start out by taking random actions. Sometimes those random actions produce desired results, which earn them rewards. Via trial-and-error on a massive scale, they can learn sophisticated strategies.
In the context of games, this process can be abetted by having the AI play against another version of itself, ensuring that the opponents will be evenly matched. It also locks the AI into a process of one-upmanship, where any new strategy that emerges forces the opponent to search for a countermeasure. Over time, this “self-play” amounted to what the researchers call an “auto-curriculum.”
According to OpenAI researcher Igor Mordatch, this experiment shows that self-play “is enough for the agents to learn surprising behaviors on their own—it’s like children playing with each other.”
Reinforcement is a hot field of AI research right now. OpenAI’s researchers used the technique when they trained a team of bots to play the video game Dota 2, which squashed a world-champion human team last April. The Alphabet subsidiary DeepMind has used it to triumph in the ancient board game Go and the video game StarCraft.
Aniruddha Kembhavi, a researcher at the Allen Institute for Artificial Intelligence (AI2) in Seattle, says games such as hide-and-seek offer a good way for AI agents to learn “foundational skills.” He worked on a team that taught their AllenAI to play Pictionary with humans, viewing the gameplay as a way for the AI to work on common sense reasoning and communication. “We are, however, quite far away from being able to translate these preliminary findings in highly simplified environments into the real world,” says Kembhavi.
Illustration: OpenAI
AI agents construct a fort during a hide-and-seek game developed by OpenAI.
In OpenAI’s game of hide-and-seek, both the hiders and the seekers received a reward only if they won the game, leaving the AI players to develop their own strategies. Within a simple 3D environment containing walls, blocks, and ramps, the players first learned to run around and chase each other (strategy 1). The hiders next learned to move the blocks around to build forts (2), and then the seekers learned to move the ramps (3), enabling them to jump inside the forts. Then the hiders learned to move all the ramps into their forts before the seekers could use them (4).
The two strategies that surprised the researchers came next. First the seekers learned that they could jump onto a box and “surf” it over to a fort (5), allowing them to jump in—a maneuver that the researchers hadn’t realized was physically possible in the game environment. So as a final countermeasure, the hiders learned to lock all the boxes into place (6) so they weren’t available for use as surfboards.
Illustration: OpenAI
An AI agent uses a nearby box to surf its way into a competitor’s fort.
In this circumstance, having AI agents behave in an unexpected way wasn’t a problem: They found different paths to their rewards, but didn’t cause any trouble. However, you can imagine situations in which the outcome would be rather serious. Robots acting in the real world could do real damage. And then there’s Nick Bostrom’s famous example of a paper clip factory run by an AI, whose goal is to make as many paper clips as possible. As Bostrom told IEEE Spectrum back in 2014, the AI might realize that “human bodies consist of atoms, and those atoms could be used to make some very nice paper clips.”
Bowen Baker, another member of the OpenAI research team, notes that it’s hard to predict all the ways an AI agent will act inside an environment—even a simple one. “Building these environments is hard,” he says. “The agents will come up with these unexpected behaviors, which will be a safety problem down the road when you put them in more complex environments.”
AI researcher Katja Hofmann at Microsoft Research Cambridge, in England, has seen a lot of gameplay by AI agents: She started a competition that uses Minecraft as the playing field. She says the emergent behavior seen in this game, and in prior experiments by other researchers, shows that games can be a useful for studies of safe and responsible AI.
“I find demonstrations like this, in games and game-like settings, a great way to explore the capabilities and limitations of existing approaches in a safe environment,” says Hofmann. “Results like these will help us develop a better understanding on how to validate and debug reinforcement learning systems–a crucial step on the path towards real-world applications.”
Baker says there’s also a hopeful takeaway from the surprises in the hide-and-seek experiment. “If you put these agents into a rich enough environment they will find strategies that we never knew were possible,” he says. “Maybe they can solve problems that we can’t imagine solutions to.” Continue reading
Posted in Human Robots
#435664 Swarm Robots Mimic Ant Jaws to Flip and ...
Small robots are appealing because they’re simple, cheap, and it’s easy to make a lot of them. Unfortunately, being simple and cheap means that each robot individually can’t do a whole lot. To make up for this, you can do what insects do—leverage that simplicity and low-cost to just make a huge swarm of simple robots, and together, they can cooperate to carry out relatively complex tasks.
Using insects as an example does set a bit of an unfair expectation for the poor robots, since insects are (let’s be honest) generally smarter and much more versatile than a robot on their scale could ever hope to be. Most robots with insect-like capabilities (like DASH and its family) are really too big and complex to be turned into swarms, because to make a vast amount of small robots, things like motors aren’t going to work because they’re too expensive.
The question, then, is to how to make a swarm of inexpensive small robots with insect-like mobility that don’t need motors to get around, and Jamie Paik’s Reconfigurable Robotics Lab at EPFL has an answer, inspired by trap-jaw ants.
Let’s talk about trap-jaw ants for just a second, because they’re insane. You can read this 2006 paper about them if you’re particularly interested in insane ants (and who isn’t!), but if you just want to hear the insane bit, it’s that trap-jaw ants can fire themselves into the air by biting the ground (!). In just 0.06 millisecond, their half-millimeter long mandibles can close at a top speed of 64 meters per second, which works out to an acceleration of about 100,000 g’s. Biting the ground causes the ant’s head to snap back with a force of 300 times the body weight of the ant itself, which launches the ant upwards. The ants can fly 8 centimeters vertically, and up to 15 cm horizontally—this is a lot, for an ant that’s just a few millimeters long.
Trap-jaw ants can fire themselves into the air by biting the ground, causing the ant’s head to snap back with a force of 300 times the body weight of the ant itself
EPFL’s robots, called Tribots, look nothing at all like trap-jaw ants, which personally I am fine with. They’re about 5 cm tall, weighing 10 grams each, and can be built on a flat sheet, and then folded into a tripod shape, origami-style. Or maybe it’s kirigami, because there’s some cutting involved. The Tribots are fully autonomous, meaning they have onboard power and control, including proximity sensors that allow them to detect objects and avoid them.
Photo: Marc Delachaux/EPFL
EPFL researchers Zhenishbek Zhakypov and Jamie Paik.
Avoiding objects is where the trap-jaw ants come in. Using two different shape-memory actuators (a spring and a latch, similar to how the ant’s jaw works), the Tribots can move around using a bunch of different techniques that can adapt to the terrain that they’re on, including:
Vertical jumping for height
Horizontal jumping for distance
Somersault jumping to clear obstacles
Walking on textured terrain with short hops (called “flic-flac” walking)
Crawling on flat surfaces
Here’s the robot in action:
Tribot’s maximum vertical jump is 14 cm (2.5 times its height), and horizontally it can jump about 23 cm (almost 4 times its length). Tribot is actually quite efficient in these movements, with a cost of transport much lower than similarly-sized robots, on par with insects themselves.
Working together, small groups of Tribots can complete tasks that a single robot couldn’t do alone. One example is pushing a heavy object a set distance. It turns out that you need five Tribots for this task—a leader robot, two worker robots, a monitor robot to measure the distance that the object has been pushed, and then a messenger robot to relay communications around the obstacle.
Image: EPFL
Five Tribots collaborate to move an object to a desired position, using coordination between a leader, two workers, a monitor, and a messenger robot. The leader orders the two worker robots to push the object while the monitor measures the relative position of the object. As the object blocks the two-way link between the leader and the monitor, the messenger maintains the communication link.
The researchers acknowledge that the current version of the hardware is limited in pretty much every way (mobility, sensing, and computation), but it does a reasonable job of demonstrating what’s possible with the concept. The plan going forward is to automate fabrication in order to “enable on-demand, ’push-button-manufactured’” robots.
“Designing minimal and scalable insect-inspired multi-locomotion millirobots,” by Zhenishbek Zhakypov, Kazuaki Mori, Koh Hosoda, and Jamie Paik from EPFL and Osaka University, is published in the current issue of Nature.
[ RRL ] via [ EPFL ] Continue reading
Posted in Human Robots
#435628 Soft Exosuit Makes Walking and Running ...
Researchers at Harvard’s Wyss Institute have been testing a flexible, lightweight exosuit that can improve your metabolic efficiency by 4 to 10 percent while walking and running. This is very important because, according to a press release from Harvard, the suit can help you be faster and more efficient, whether you’re “walking at a leisurely pace,” or “running for your life.” Great!
Making humans better at running for their lives is something that we don’t put nearly enough research effort into, I think. The problem may not come up very often, but when it does, it’s super important (because, bears). So, sign me up for anything that we can do to make our desperate flights faster or more efficient—especially if it’s a lightweight, wearable exosuit that’s soft, flexible, and comfortable to wear.
This is the same sort of exosuit that was part of a DARPA program that we wrote about a few years ago, which was designed to make it easier for soldiers to carry heavy loads for long distances.
Photos: Wyss Institute at Harvard University
The system uses two waist-mounted electrical motors connected with cables to thigh straps that run down around your butt. The motors pull on the cables at the same time that your muscles actuate, helping them out and reducing the amount of work that your muscles put in without decreasing the amount of force they exert on your legs. The entire suit (batteries included) weighs 5 kilograms (11 pounds).
In order for the cables to actuate at the right time, the suit tracks your gait with two inertial measurement units (IMUs) on the thighs and one on the waist, and then adjusts its actuation profile accordingly. It works well, too, with measurable increases in performance:
We show that a portable exosuit that assists hip extension can reduce the metabolic rate of treadmill walking at 1.5 meters per second by 9.3 percent and that of running at 2.5 meters per second by 4.0 percent compared with locomotion without the exosuit. These reduction magnitudes are comparable to the effects of taking off 7.4 and 5.7 kilograms during walking and running, respectively, and are in a range that has shown meaningful athletic performance changes.
By increasing your efficiency, you can think of the suit as being able to make you walk or run faster, or farther, or carry a heavier load, all while spending the same amount of energy (or less), which could be just enough to outrun the bear that’s chasing you. Plus, it doesn’t appear to be uncomfortable to wear, and doesn’t require the user to do anything differently, which means that (unlike most robotics things) it’s maybe actually somewhat practical for real-world use—whether you’re indoors or outdoors, or walking or running, or being chased by a bear or not.
Sadly, I have no idea when you might be able to buy one of these things. But the researchers are looking for ways to make the suit even easier to use, while also reducing the weight and making the efficiency increase more pronounced. Harvard’s Conor Walsh says they’re “excited to continue to apply it to a range of applications, including assisting those with gait impairments, industry workers at risk of injury performing physically strenuous tasks, or recreational weekend warriors.” As a weekend warrior who is not entirely sure whether he can outrun a bear, I’m excited for this.
Reducing the metabolic rate of walking and running with a versatile, portable exosuit, by Jinsoo Kim, Giuk Lee, Roman Heimgartner, Dheepak Arumukhom Revi, Nikos Karavas, Danielle Nathanson, Ignacio Galiana, Asa Eckert-Erdheim, Patrick Murphy, David Perry, Nicolas Menard, Dabin Kim Choe, Philippe Malcolm, and Conor J. Walsh from the Wyss Institute for Biologically Inspired Engineering at Harvard University, appears in the current issue of Science. Continue reading
Posted in Human Robots
#435541 This Giant AI Chip Is the Size of an ...
People say size doesn’t matter, but when it comes to AI the makers of the largest computer chip ever beg to differ. There are plenty of question marks about the gargantuan processor, but its unconventional design could herald an innovative new era in silicon design.
Computer chips specialized to run deep learning algorithms are a booming area of research as hardware limitations begin to slow progress, and both established players and startups are vying to build the successor to the GPU, the specialized graphics chip that has become the workhorse of the AI industry.
On Monday Californian startup Cerebras came out of stealth mode to unveil an AI-focused processor that turns conventional wisdom on its head. For decades chip makers have been focused on making their products ever-smaller, but the Wafer Scale Engine (WSE) is the size of an iPad and features 1.2 trillion transistors, 400,000 cores, and 18 gigabytes of on-chip memory.
The Cerebras Wafer-Scale Engine (WSE) is the largest chip ever built. It measures 46,225 square millimeters and includes 1.2 trillion transistors. Optimized for artificial intelligence compute, the WSE is shown here for comparison alongside the largest graphics processing unit. Image Credit: Used with permission from Cerebras Systems.
There is a method to the madness, though. Currently, getting enough cores to run really large-scale deep learning applications means connecting banks of GPUs together. But shuffling data between these chips is a major drain on speed and energy efficiency because the wires connecting them are relatively slow.
Building all 400,000 cores into the same chip should get round that bottleneck, but there are reasons it’s not been done before, and Cerebras has had to come up with some clever hacks to get around those obstacles.
Regular computer chips are manufactured using a process called photolithography to etch transistors onto the surface of a wafer of silicon. The wafers are inches across, so multiple chips are built onto them at once and then split up afterwards. But at 8.5 inches across, the WSE uses the entire wafer for a single chip.
The problem is that while for standard chip-making processes any imperfections in manufacturing will at most lead to a few processors out of several hundred having to be ditched, for Cerebras it would mean scrapping the entire wafer. To get around this the company built in redundant circuits so that even if there are a few defects, the chip can route around them.
The other big issue with a giant chip is the enormous amount of heat the processors can kick off—so the company has had to design a proprietary water-cooling system. That, along with the fact that no one makes connections and packaging for giant chips, means the WSE won’t be sold as a stand-alone component, but as part of a pre-packaged server incorporating the cooling technology.
There are no details on costs or performance so far, but some customers have already been testing prototypes, and according to Cerebras results have been promising. CEO and co-founder Andrew Feldman told Fortune that early tests show they are reducing training time from months to minutes.
We’ll have to wait until the first systems ship to customers in September to see if those claims stand up. But Feldman told ZDNet that the design of their chip should help spur greater innovation in the way engineers design neural networks. Many cornerstones of this process—for instance, tackling data in batches rather than individual data points—are guided more by the hardware limitations of GPUs than by machine learning theory, but their chip will do away with many of those obstacles.
Whether that turns out to be the case or not, the WSE might be the first indication of an innovative new era in silicon design. When Google announced it’s AI-focused Tensor Processing Unit in 2016 it was a wake-up call for chipmakers that we need some out-of-the-box thinking to square the slowing of Moore’s Law with skyrocketing demand for computing power.
It’s not just tech giants’ AI server farms driving innovation. At the other end of the spectrum, the desire to embed intelligence in everyday objects and mobile devices is pushing demand for AI chips that can run on tiny amounts of power and squeeze into the smallest form factors.
These trends have spawned renewed interest in everything from brain-inspired neuromorphic chips to optical processors, but the WSE also shows that there might be mileage in simply taking a sideways look at some of the other design decisions chipmakers have made in the past rather than just pumping ever more transistors onto a chip.
This gigantic chip might be the first exhibit in a weird and wonderful new menagerie of exotic, AI-inspired silicon.
Image Credit: Used with permission from Cerebras Systems. Continue reading
Posted in Human Robots