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 method transforms shapeson October 18, 2019 at 10:49 am
Turning a chair into a table, or vice versa, might sound like somewhat of a magic trick. In this case, zero magic is involved, just plenty of complex geometry and machine learning. Called LOGAN, the ...
- Designing Scalable HPC, Deep Learning, Big Data, and Cloud Middleware for Exascale Systemson October 18, 2019 at 8:05 am
In this video from the UK HPC Conference, DK Panda from Ohio State University presents: Designing Scalable HPC, Deep Learning, Big Data, and Cloud Middleware for Exascale Systems. This talk will focus ...
- Cognex Acquires SUALAB to Enhance Deep Learning Solutionson October 18, 2019 at 6:50 am
Cognex CGNX recently announced the acquisition of Seoul-based SUALAB, a developer of deep learning-based vision software. Although the financial terms of the acquisition have been kept under wraps, ...
- StradVision VP of Engineering Dr. Jaewon Sung unveils latest deep-learning innovations for Autonomous Vehicles at Seoul eventon October 17, 2019 at 5:46 pm
The event, hosted by tech giant NVIDIA, drew a wide variety of attendees from NVIDIA's Korean Inception Program — which accelerates the growth of more than 4,000 cutting-edge AI startups by offering ...
- NASA Uses Deep Learning to Monitor Solar Weatheron October 17, 2019 at 3:31 pm
Accurately monitoring space weather, however, can be difficult, expensive and unreliable. Now, NASA’s Frontier Development Lab (FDL) has developed a new method, based on deep learning, that allows ...
- Deep Learning in Drug Discovery and Diagnostics Market To Flourish at Massive CAGR By 2026on October 16, 2019 at 9:03 pm
Oct 17, 2019 (WiredRelease via COMTEX) -- Deep learning is branch of machine learning that investigates large volumes of organized and unorganized data. The approach also analyzes multi-dimensional ...
- Best of arXiv.org for AI, Machine Learning, and Deep Learning – September 2019on October 16, 2019 at 8:17 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 ...
- When to use Machine Learning or Deep Learning?on October 16, 2019 at 6:33 am
In both machine learning and deep learning, engineers use software tools, such as MATLAB, to enable computers to identify trends and characteristics in data by learning from an example data set. In ...
- Vector Institute appoints eight new Faculty Members, Announces Plans to Recruit Three new Faculty in Deep Learning with the University of Torontoon October 16, 2019 at 5:49 am
TORONTO, Oct. 16, 2019 /CNW/ - Today, the Vector Institute announced that it will work with the University of Toronto to recruit three new tenure-stream faculty positions in deep learning. Announced ...
via Bing News