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
- Does AI Truly Learn And Why We Need to Stop Overhyping Deep Learning on December 15, 2018 at 7:20 pm
AI today is described in breathless terms as computer algorithms that use silicon incarnations of our organic brains to learn and reason about the world, intelligent superhumans rapidly making their c... […]
- LF Deep Learning Foundation brings on deep learning framework on December 14, 2018 at 8:21 am
Uber’s open-source distributed training framework Horovod is joining the LF Deep Learning Foundation to support its work in artificial intelligence, machine learning and deep learning. […]
- Uber contributes its Horovod deep learning system to the Linux Foundation on December 13, 2018 at 12:32 pm
Engineers at the world’s top tech firms often find themselves having to build custom alternatives to existing software in order to meet the unique needs of their companies. One notable example ... […]
- Diving Into Deep Learning – Key Things Every Business Leader Needs To Know on December 13, 2018 at 9:50 am
Despite complexities of the human brain, scientists today are ostensibly creating one from scratch with one subset of artificial intelligence called deep learning. The basic building blocks of deep le... […]
- LF Deep Learning Welcomes Horovod Distributed Training Framework as Newest Project on December 13, 2018 at 9:28 am
SEATTLE, Dec. 13, 2018 /PRNewswire/ -- KubeCon + CloudNativeCon North America --The LF Deep Learning Foundation, a community umbrella project of The Linux Foundation that supports and sustains open so... […]
- Global Deep Learning Chipset Market In-depth Evaluation on Growth, Share, Size and Trends Until the End of 2025 on December 12, 2018 at 9:25 pm
Akin to Artificial Intelligence (AI), the concept and possibilities of deep learning are being contemplated and harnessed for several decades. But, in the recent times, the technology pertaining to al... […]
- insideBIGDATA Guide to Data Platforms for Artificial Intelligence and Deep Learning – Part 5 on December 12, 2018 at 2:32 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... […]
- How deep learning is bringing automatic cloud detection to new heights on December 12, 2018 at 12:49 pm
Clouds come in all shapes and sizes, and now a deep learning model can help detect the finer details in cloud data. Credit: Adriel Kloppenburg on Unsplash Kids lying on their backs in a grassy ... […]
- Deep-learning technique reveals ‘invisible’ objects in the dark on December 12, 2018 at 6:17 am
Small imperfections in a wine glass or tiny creases in a contact lens can be tricky to make out, even in good light. In almost total darkness, images of such transparent features or objects are nearly ... […]
via Bing News