Researchers at the U.S. Army Research Laboratory and the University of Texas at Austin have developed new techniques for robots or computer programs to learn how to perform tasks by interacting with a human instructor.
The findings of the study will be presented and published at the Association for the Advancement of Artificial Intelligence Conference in New Orleans, Louisiana, Feb. 2-7.
ARL and UT researchers considered a specific case where a human provides real-time feedback in the form of critique. First introduced by collaborator Dr. Peter Stone, a professor at the University of Texas at Austin, along with his former doctoral student, Brad Knox, as TAMER, or Training an Agent Manually via Evaluative Reinforcement, the ARL/UT team developed a new algorithm called Deep TAMER.
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.
According to Army researcher Dr. Garrett Warnell, the team considered situations where a human teaches an agent how to behave by observing it and providing critique, for example, “good job” or “bad job” -similar to the way a person might train a dog to do a trick. 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.
Many current techniques in artificial intelligence require robots to interact with their environment for extended periods of time to learn how to optimally perform a task. During this process, the agent might perform actions that may not only be wrong, like a robot running into a wall for example, but catastrophic like a robot running off the side of a cliff. Warnell said help from humans will speed things up for the agents, and help them avoid potential pitfalls.
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. Deep-TAMER-trained agents exhibited superhuman performance, besting both their amateur trainers and, on average, an expert human Atari player.
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.
Their work will be published in the AAAI 2018 conference proceedings.
“The Army of the future will consist of Soldiers and autonomous teammates working side-by-side,” Warnell said. “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.”
Deep TAMER is the first step in a line of research its researchers envision will enable more successful human-autonomy teams in the Army. Ultimately, they want autonomous agents that can quickly and safely learn from their human teammates in a wide variety of styles such as demonstration, natural language instruction and critique.
The Latest on: Deep Learning
Google releases the deep learning model that allows for features like the Pixel 2’s Portrait Mode
on March 17, 2018 at 12:08 am
This deep learning model assigns semantic labels to every pixel in an image. In turn, categorization allows classifications like road, sky, person, or dog, and which part of a picture is the background and what is the foreground. Applied to photography ... […]
Best of arXiv.org for AI, Machine Learning, and Deep Learning – February 2018
on March 16, 2018 at 12:35 pm
In this recurring monthly feature, we filter recent research papers appearing on the arXiv.org preprint server for compelling subjects relating to AI, machine learning and deep learning – from disciplines including statistics, mathematics and computer ... […]
Beyond the Hype: AI, ML, and Deep Learning in Cybersecurity (Part 2)
on March 16, 2018 at 11:15 am
Insight for I&O leaders on deploying AIOps platforms to enhance performance monitoring today. Read the Guide. This is the second piece of nature of my three-part blog on the topic of the human intelligence vs. AI, understanding the vocabulary in use today ... […]
Using Python to Snake Closer to Simplified Deep Learning
on March 15, 2018 at 10:14 am
On today’s episode of “The Interview” with The Next Platform, we discuss the role of higher level interfaces to common machine learning and deep learning frameworks, including Caffe. Despite the existence of multiple deep learning frameworks, there ... […]
How to train and deploy deep learning at scale
on March 15, 2018 at 6:58 am
Check out the "Scalable deep learning" session at the Artificial Intelligence Conference in New York, April 29-May 2, 2018. Hurry—early price ends March 16. I would say that you hear a lot about the modeling of problems associated with deep learning. […]
A Crash Course in Deep Learning
on March 14, 2018 at 5:54 pm
Artificial Intelligence (AI) is solving problems that seemed well beyond our reach just a few years back. Using deep learning, the fastest growing segment of AI, computers are now able to learn and recognize patterns from data that were considered too ... […]
global deep learning system market scrutinized in new research
on March 14, 2018 at 2:13 am
The 2018 market research report on Global Deep Learning System Market is an in-depth study and analysis of the market by our industry experts with unparalleled domain knowledge. The Global Deep Learning System Industry report provides key information about ... […]
3 Competitive Advantages of Deep Learning for Your Company
on March 12, 2018 at 6:00 am
What do you think of when you hear about AI? Do you picture your favorite sci-fi movie or a book that you read when you were younger? In that favorite book or movie, were the robots smart? Could they learn? Today’s software robots can. In AI, we can find ... […]
Deep Learning Aims to Upgrade Your Smartphone's Brain
on March 12, 2018 at 12:06 am
The advertising world loves big, shiny, techy things. Agency and client ears perk right up when they hear about virtual reality kiosks, gadget-filled activations and holograms of dead rock stars. But then there are the tech innovations that sound a bit, or ... […]
via Google News and Bing News