Tag Archives: many
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.
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.
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
We humans spend most of our time getting hungry or eating, which must be really inconvenient for the people who have to produce food for everyone. For a sustainable and tasty future, we’ll need to make the most of what we’ve got by growing more food with less effort, and that’s where the robots can help us out a little bit.
FarmWise, a California-based startup, is looking to enhance farming efficiency by automating everything from seeding to harvesting, starting with the worst task of all: weeding. And they’ve just raised US $14.5 million to do it.
FarmWise’s autonomous, AI-enabled robots are designed to solve farmers’ most pressing challenges by performing a variety of farming functions – starting with weeding, and providing personalized care to every plant they touch. Using machine learning models, computer vision and high-precision mechanical tools, FarmWise’s sophisticated robots cleanly pick weeds from fields, leaving crops with the best opportunity to thrive while eliminating harmful chemical inputs. To date, FarmWise’s robots have efficiently removed weeds from more than 10 million plants.
FarmWise is not the first company to work on large mobile farming robots. A few years ago, we wrote about DeepField Robotics and their giant weed-punching robot. But considering how many humans there are, and how often we tend to get hungry, it certainly seems like there’s plenty of opportunity to go around.
FarmWise is collecting massive amounts of data about every single plant in an entire field, which is something that hasn’t been possible before. Above, one of the robots at a farm in Salinas Valley, Calif.
Weeding is just one thing that farm robots are able to do. FarmWise is collecting massive amounts of data about every single plant in an entire field, practically on the per-leaf level, which is something that hasn’t been possible before. Data like this could be used for all sorts of things, but generally, the long-term hope is that robots could tend to every single plant individually—weeding them, fertilizing them, telling them what good plants they are, and then mercilessly yanking them out of the ground at absolute peak ripeness. It’s not realistic to do this with human labor, but it’s the sort of data-intensive and monotonous task that robots could be ideal for.
The question with robots like this is not necessarily whether they can do the job that they were created for, because generally, they can—farms are structured enough environments that they lend themselves to autonomous robots, and the tasks are relatively well defined. The issue right now, I think, is whether robots are really time- and cost-effective for farmers. Capable robots are an expensive investment, and even if there is a shortage of human labor, will robots perform well enough to convince farmers to adopt the technology? That’s a solid maybe, and here’s hoping that FarmWise can figure out how to make it work.
[ FarmWise ] Continue reading
Illustration: John MacNeill
Engineers and Architects Are Already Designing Lunar Habitats
Squeezing Rocket Fuel From Moon Rocks
Robots Will Navigate the Moon With Maps They Make Themselves
Kim Stanley Robinson Built a Moon Base in His Mind
The most valuable natural resource on the moon may be water. In addition to sustaining lunar colonists, it could also be broken down into its constituent elements—hydrogen and oxygen—and used to make rocket propellant.
Although the ancients called the dark areas on the moon maria (Latin for “seas”), it has long been clear that liquid water can’t exist on the lunar surface, where it would swiftly evaporate. Since the 1960s, though, scientists have hypothesized that the moon indeed harbors water, in the form of ice. Because the moon has a very small axial tilt—just 1.5 degrees—the floors of many polar craters remain in perpetual darkness. Water could thus condense and survive in such polar “cold traps,” where it might one day be mined.
Water Water Everywhere: Finding rich deposits of ice and extracting it should be possible but will be technically challenging for lunar settlers. Illustration: John MacNeill
Mapping the Moon: Several lunar missions have produced strong evidence of water ice. A NASA instrument called the Moon Mineralogy Mapper (M3) found indications of water ice on the permanently shadowed floors of some polar craters. However, the measurements suggest that only a small fraction of cold traps contain ice [colored areas], and that the ice is probably mixed with lunar regolith. Data source.
Rover-Mounted Drill: The most straightforward strategy for extracting water from polar ice deposits uses a rover-mounted drill. Honeybee Robotics has designed a Planetary Volatiles Extractor with a heated auger, which would cause any water ice in the drilled regolith to vaporize. That vapor would then move through a tube to a condenser unit, where it would turn back into ice. Illustration: John MacNeill
Thermal Mining: A more ambitious scheme for extracting water from the moon is “thermal mining.” Researchers at the Colorado School of Mines have proposed redirecting the sun’s rays , using heliostats mounted on a crater rim. Water trapped in the regolith would turn into vapor that would be collected in a large tent, then vented into refrigerated cold traps, where it would condense as pure water ice. Illustration: John MacNeill
Compressed-Gas Transport: To produce rocket fuel from water ice would require an electrolyzer to break the water into hydrogen and oxygen, which would then be compressed and stored for later use. In situ production would also require vehicles to transport the processed fuel to rocket pads. Illustration: John MacNeill
Next Continue reading