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
- Google Cloud launches Deep Learning Containers in betaon June 26, 2019 at 1:21 pm
Google Cloud Platform (GCP) today launched Deep Learning Containers, environments optimized for deploying and testing applications and services that utilize machine learning. GCP Deep Learning ... […]
- Best of arXiv.org for AI, Machine Learning, and Deep Learning – May 2019on June 26, 2019 at 11:34 am
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 ... […]
- Machine Learning With Python From MIT on edXon June 26, 2019 at 9:09 am
Python is widely acknowledged as the most suitable programming language for this sphere and this courses sets out to be an in-depth introduction to the field of machine learning, from linear models to ... […]
- Cortex Launches Deep Learning and AI Network for Decentralized Appson June 26, 2019 at 6:21 am
Cortex claims that this is the first time that artificial intelligence has been introduced to a crypto network at scale. Cortex has launched a network for decentralized apps powered by artificial ... […]
- Dynamic Sampling Of Video To Imagery For Deep Learningon June 25, 2019 at 5:19 pm
While today’s deep learning systems are able to natively analyze video, the large file sizes of high resolution movies present unique challenges in terms of storage space and computational ... […]
- Blue Hexagon Unveils Native Deep Learning-Powered Threat Protection Platform For Amazon Web Serviceson June 25, 2019 at 2:12 pm
Industry’s leading deep learning-based threat protection now supports AWS VPC traffic mirroring to further secure AWS enterprise cloud deployments against cyberthreats Blue Hexagon, a deep ... […]
- Deep Learning Market 2019 Segmentation along with Regional Outlook, Competitive Strategies, Factors Contributing to Growthon June 25, 2019 at 2:03 am
Jun 25, 2019 (The Expresswire via COMTEX) -- Deep Learning Market Report includes data about consumer perspective, comprehensive analysis, statistics, market share, company performances (Stocks), ... […]
- We Must Recognize Just How Brittle And Unpredictable Today's Correlative Deep Learning AI Ison June 24, 2019 at 1:20 pm
AI is everywhere today. It has become the modern-day fairy dust sprinkled over any and every project no matter how little relevance it holds to the task at hand. Robust hand-coded rulesets and stable ... […]
- How Deep Learning Is Transforming Brain Mappingon June 24, 2019 at 7:00 am
Thanks to deep learning, the tricky business of making brain atlases just got a lot easier. Brain maps are all the rage these days. From rainbow-colored dots that highlight neurons or gene expression ... […]
via Bing News