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
via Google News
The Latest on: Deep Learning
- Deep learning architectures for prediction of nucleosome positioning from sequences data on December 9, 2018 at 1:56 pm
Nucleosomes are DNA-histone complex, each wrapping about 150 pairs of double-stranded DNA. Their function is fundamental for one of the primary functions of Chromatin i.e. packing the DNA into the nuc... […]
- Deep Learning Market – Latest Report on Upcoming Industry Trends 2025 on December 7, 2018 at 8:35 pm
The scope of deep learning technology traverses across the areas of artificial intelligence, machine learning, and big data analytics, yet is quite distinct from each of them. In recent years, the app... […]
- Research into 'deep-learning computers' at Case Western Reserve University is cited among 2018's most significant medical breakthroughs on December 7, 2018 at 10:27 am
The work of researchers at Case Western Reserve University is highlighted in this story on Prevention.com spotlighting "the 10 most incredible medical breakthroughs of 2018." "From medical drones to t... […]
- Recreate your favorite paintings using deep learning and 3-D printing on December 6, 2018 at 4:32 pm
The empty frames hanging inside the Isabella Stewart Gardner Museum serve as a tangible reminder of the world's biggest unsolved art heist. While the original masterpieces may never be recovered, a te... […]
- insideBIGDATA Guide to Data Platforms for Artificial Intelligence and Deep Learning – Part 4 on December 5, 2018 at 12:55 pm
With AI and DL, storage is cornerstone to handling the deluge of data constantly generated in today’s hyperconnected world. It is a vehicle that captures and shares data to create business value. In t... […]
- Gannett Is Using Deep Learning to Determine Why Certain Ad Designs Work on December 5, 2018 at 12:13 pm
Gannett is turning to a form of artificial intelligence to design better online ads. The USA Today publisher recently rolled out a new internal platform that uses deep learning and computer vision to ... […]
- Deep learning Slack bot Meeshkan wins Slush 100 startup competition on December 5, 2018 at 8:37 am
Meeshkan, a company whose Slack bot helps engineers monitor and train machine learning models made with popular frameworks like PyTorch and TensorFlow without leaving the team chat app. […]
- Out of shape? Deep learning works differently than we thought on December 5, 2018 at 8:29 am
Unlike humans, AI object recognition pays a lot of attention to small details—and misses the broader picture. But there are ways to close the gap. If you look at the image below, which animal ... […]
- Deep Learning — Ethereum for Developer on December 4, 2018 at 11:23 pm
Hello World, welcome to “Deep Learning” series. In which we hands on Ethereum Blockchain.Trying to explain bits and bytes of Ethereum in this series ,thats begin with simplifying the common ... […]
via Bing News