AI News, New algorithms to train robots

New algorithms to train robots

It is an extension of TAMER that uses deep learning -- a class of machine learning algorithms that are loosely inspired by the brain to provide a robot the ability to learn how to perform tasks by viewing video streams in a short amount of time with a human trainer.

Warnell said the researchers extended earlier work in this field to enable this type of training for robots or computer programs that currently see the world through images, which is an important first step in designing learning agents that can operate in the real world.

As a first step, the researchers demonstrated Deep TAMER's success by using it with 15 minutes of human-provided feedback to train an agent to perform better than humans on the Atari game of bowling -- a task that has proven difficult for even state-of-the-art methods in artificial intelligence.

Within the next one to two years, researchers are interested in exploring the applicability of their newest technique in a wider variety of environments: for example, video games other than Atari Bowling and additional simulation environments to better represent the types of agents and environments found when fielding robots in the real world.

ARL and UT Researchers Enhance Robot Training

U.S. Army researcher Dr. Garrett Warnell explained that the human trainers provide critique to gauge a robot’s progress during training, with phrases such as “good job” or “bad job” as a human might do when training a canine companion.

Warnell said the researchers extended earlier work in this field to enable this type of training for robots or computer programs that currently see the world through images, which is an important first step in designing learning agents that can operate in the real world.

“While both humans and autonomous agents can be trained in advance, the team will inevitably be asked to perform tasks—for example, search and rescue or surveillance—in new environments they have not seen before.

In these situations, humans are remarkably good at generalizing their training, but current artificially intelligent agents are not.” The U.S. Army is hoping that Deep TAMER is an enabling technology for more successful human-robotic-autonomous-system teams in the future.

An ultimate goal is to create autonomous agents capable of quickly learning new skills and functions from human teammates, using training methods that may be based on different actions, including graphics and sign language.

Training a Robot via Human Feedback

In this MIT Media Lab "Labcast" we describe work by Postdoctoral Researcher Brad Knox to allow even technically unskilled users to train our robots.

New AI system can train robots for armies

Scientists develop that will teach robots and computer programmes to interact with a human instructor for the purpose. Scientists have developed an artificial ...

अब सीमा पर तैनात होंगे रोबोट, लेंगे दुश्मन से लोहा

U.S. Army researchers, in cooperation with university scientists, have developed new techniques to train robots or computer programs to perform tasks under the ...