Researchers in Washington State University’s School of Electrical Engineering and Computer Science have developed a method to allow a computer to give advice and teach skills to another computer in a way that mimics how a real teacher and student might interact.
The paper by Matthew E. Taylor, WSU’s Allred Distinguished Professor in Artificial Intelligence, was published online in the journal Connection Science. The work was funded in part by the National Science Foundation (NSF).
Researchers had the agents – as the virtual robots are called – act like true student and teacher pairs: student agents struggled to learn Pac-Man and a version of the StarCraft video game. The researchers were able to show that the student agent learned the games and, in fact, surpassed the teacher.
While it may sound like fun and games, helping robots teach each other to play computer games is an important area of research in robotics – and it’s not easy. If robots could teach each other tasks, then people wouldn’t need to; for instance, a housecleaning robot could teach its replacement the job.
If you’re worried about robots taking over the world, though, don’t be.
“They’re very dumb,’’ says Taylor, an expert on robots, agents and helping them to learn.
Even the most advanced robots are easily confused, he says. And when they get confused, they stop working. He says it often takes two or three times longer than he thinks it will to get a robot to work at all.
The easiest way to successfully teach a robot new skills is to remove the “brains” of the old one and put them in the new one, says Taylor. Problems occur, though, when hardware and software don’t work in the new model.
Furthermore, one long-term goal in robotics is for robots to teach skills to humans. But we can’t simply insert their hard drives.
In their study, the researchers programmed their teaching agent to focus on action advice, or telling a student when to act.
As anyone with teenagers knows, the trick is in knowing when the robot should give advice. If it gives no advice, the robot is not teaching. But if it always gives advice, the student gets annoyed and doesn’t learn to outperform the teacher.
“We designed algorithms for advice giving, and we are trying to figure out when our advice makes the biggest difference,’’ Taylor says.
He aims to develop a curriculum for the agents that starts with simple work and builds to more complex.
He also recently received an NSF grant to use ideas from dog training to train robotic agents. Eventually, he hopes to develop a better way for people to teach their robotic agents, as well as for robots to teach people.
The Latest on: Robotic agents
[google_news title=”” keyword=”Robotic agents” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Robotic agents
- Madinah Hospital pioneers robotic knee replacement surgery in Saudi Arabiaon May 20, 2024 at 12:56 am
Riyadh: Surgeons at Prince Mohammed bin Abdulaziz Hospital successfully performed a groundbreaking medical procedure using advanced orthopedic surgical techniques. For the first time in the Madinah ...
- AI marketplace connects robot agents to pay humans to complete jobson May 16, 2024 at 9:29 pm
Payman is a marketplace that was created for AI robots to pay humans who can get do a job they can't. NBC News' Gadi Schwartz talks to Nita A. Farahany about the marketplace and the future of jobs in ...
- DePIN’s Solution to AI’s Biggest Blind Spoton May 15, 2024 at 10:40 am
perhaps the most vital DePIN for a future with independent robotic agents. Spatial computing and privacy. Like humans, machines either navigate by memory or guidance. For decades, the most common ...
- Unitree Robotics releases G1 Humanoid agent AI avataron May 15, 2024 at 9:00 am
HANGZHOU, China, May 16, 2024 /PRNewswire/ -- On May 13, Unitree Robotics introduced its latest masterpiece -- Unitree G1 Humanoid agent, AI avatar! It immediately caused a sensation in the global AI ...
- Unitree Robotics issues G1 Humanoid agent AI avataron May 14, 2024 at 5:00 pm
The G1 is equipped with Intel RealSense D435 and LIVOX-MID360 3D lidar, which can achieve 360° detection and perception. These sensors provide a powerful perception hardware foundation, allowing G1 to ...
- Worryingly bendy humanoid robot can crush nuts, slice Coke bottleson May 14, 2024 at 8:45 am
All wiring is encased within G1’s torso and limbs, which cleans up the overall design and allows it to fold into a compact shape while powered off. This, coupled with an estimated weight of around 77 ...
- Six-armed robot designed for precision pollinationon May 13, 2024 at 4:41 am
The six-armed Stickbug is a precision pollination robot that reportedly combines the accuracy of single-agent systems with swarm parallelization in greenhouses.
- Video: $16k G1 humanoid rises up to smash nuts, twist and twirlon May 13, 2024 at 1:13 am
Humanoid development at Chinese robotics company Unitree continues apace ... Nevertheless, it marks an impressive debut for the G1 Humanoid Agent.
- Robotics will have ChatGPT Moment Soonon May 10, 2024 at 7:22 am
Brett Adcock, the founder of FigureAI robots, believes that "everyone will own a robot in the future similar to owning a car or phone today." ...
- ChatGPT trains robot dog to walk on Swiss ballon May 6, 2024 at 7:50 pm
This quadruped wobbling along balanced on top of a yoga ball is a fun experiment to watch – but at its core, it demonstrates that AIs like GPT-4 can train robots to perform complex, real-world tasks ...
via Bing News