New research used the game Overcooked to show how offline reinforcement learning algorithms could teach bots to collaborate with — or manipulate — us.
If you’ve ever cooked a complex meal with someone, you know the level of coordination required. Someone dices this, someone sautés that, as you dance around holding knives and hot pans. Meanwhile, you might wordlessly nudge each other, placing ingredients or implements within the other’s reach when you’d like something done.Research presented in late 2023 at the Neural Information Processing Systems, or NeurIPS, conference, in New Orleans, offers some clues.
But training a clueless AI from scratch to interact with people through sheer trial-and-error can waste a lot of human hours, and can even presents risks if there are, say, knives involved . Another option is to train one AI to model human behavior, then use that as a tireless human substitute for another AI to learn to interact with. Researchers have used this method in, for example, a simple game that involved entrusting a partner with monetary units.
The researchers first collected data from pairs of people playing the game. Then they trained AIs using offline RL or one of three other methods for comparison. In one method, the AI just imitated the humans. In another, it imitated the best human performances. The third method ignored the human data and had AIs practice with each other.
On the human-deliver game, training using offline RL led to an average score of 220, about 50 percent more points than the best comparison methods. On the tomato-bonus game, it led to an average score of 165, or about double the points. To support the hypothesis that the AI had learned to influence people, the paper described how when the bot wanted the human to deliver the soup, it would place a dish on the counter near the human.
Nikolaidis sees potential for the method to enhance AI-human collaboration. But he wishes that the authors had better documented the observed behaviors in the training data and exactly how the new method changed people’s behaviors to improve scores. In the future, we may be working with AI partners in kitchens, warehouses, operating rooms, battlefields and purely digital domains like writing, research and travel planning.
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Find New York-Style Slices and Beer at This New Union Market Pizza SpotThe website that Washington lives by.
Read more »
New Jersey doctor born on leap day delivers new leap babiesThis is additional taxonomy that helps us with analytics
Read more »
A New Generation of Drug Therapies Requires New Business StrategiesThe shift to advanced therapeutic modalities (ATMs) promises to change the nature of competition in the pharmaceuticals industry.
Read more »
Wild Memphis: how a new paddle-powered tour sees the musical city in a new lightA new expedition company is using sail- and paddle-powered canoes to explore the mighty Mississippi River and access the wilderness on Memphis’s doorstep.
Read more »
Missing New Jersey hiker found safe after being spotted on Ring camera in New YorkPolice said the woman regularly hikes at Ringwood State Park and was disoriented after spending the night in the woods.
Read more »
6 Months After New York Banned Airbnb, New Jersey Is Doing GreatNew York placed strict restrictions on short-term rentals last year. Rents still remain high, and some former hosts are frustrated. Meanwhile, Airbnb rentals in New Jersey are booming.
Read more »