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
- A new method to control error rates in automated species identification with deep learning algorithmson July 3, 2020 at 3:34 am
Deep Learning Algorithms (DLAs) have been increasingly used to automatically identify organisms on images. However, despite recent advances, it remains difficult to control the error rate of such ...
- Dr. Mary Yang receives $443,854 to develop deep learning methods to identify cells that promote complex disease developmenton July 2, 2020 at 2:46 pm
Dr. Mary Yang, Professor of Information Science and Director of the Midsouth Bioinformatics Center at UA Little Rock, has received $443,854 from the National Institutes of Health to develop unique ...
- MYIR Introduces Zynq UltraScale+ MPSoC Based FZ3 Card for Deep Learningon July 2, 2020 at 12:05 pm
MYIR provides FZ3 Kit as a development kit, it contains the FZ3 Card and necessary accessories including one 12V/2A power adaptor, one 16GB TF card, one mini USB cable, and one mini DP to HDMI cables ...
- Deep Learning Chip Market Revolutionary Trends in Industry Statistics by 2020-2025on July 1, 2020 at 4:23 am
The increasing investments in deep learning chip start-ups, prominence of quantum computing, and real time consumer behavior insights & increased operational efficiency are few of the factors driving ...
- Global Deep Learning Chipset Market 2020 Segmented by Application and Geography Trends, Growth and Forecasts to 2024on July 1, 2020 at 12:05 am
Global “Deep Learning Chipset Market " 2024 Research Report provide in-depth study of the present state of the ...
- Team dramatically reduces image analysis times using deep learning, other approacheson June 29, 2020 at 2:37 pm
Scientists have devised deep-learning and other approaches that dramatically reduce image-analysis times by orders of magnitude -- in some cases, matching the speed of image data acquisition itself.
- AI Weekly: A deep learning pioneer’s teachable moment on AI biason June 26, 2020 at 11:57 am
Facebook chief AI scientist Yann LeCun got into a debate with Google AI ethics co-lead Timnit Gebru about bias. Here are some key lessons to be learned.
- How Product Placement Works In 2020 - With AI, Deep Learning And Moreon June 24, 2020 at 11:35 am
Lela London chats to BEN, the Bill Gates-owned product placement agency behind most of your streaming screen's magic.
- Deep Learning Market Growth 2020, Trends, Size, Share and Forecast By 2025on June 23, 2020 at 10:47 pm
According to the latest report by IMARC Group, titled “Deep Learning Market: Global Industry Trends, Share, Size, Growth, Opportunity and Forecast 2020-2025,” the global deep learning market size is ...
via Bing News