Posted in | News | Machine-Vision

Praise Given by Robots and Virtual Agents Increases Offline Learning

Social rewards like praise have been proven to improve different stages of the learning process.

A participant training in finger-tapping task and an agent (in this figure, a robot) watching the training. Image Credit: University of Tsukuba

Scientists from Japan have now discovered that praise bestowed by artificial beings such as virtual graphics-based agents and robots can have effects comparable to praise given by humans, with key practical applications as social services, such as education, progressively moving to online and virtual platforms.

In a paper published recently in PLOS ONE, a team of scientists from the University of Tsukuba has demonstrated that motor task performance in participants was considerably improved by praise from either one or two virtual agents or robots.

Even if praise from virtual agents and robots has been observed to improve human motivation and performance during a job, whether these interactions have comparable effects on offline skill consolidation, which is a vital part of the learning process, has not been explored.

Also, the different conditions linked with the delivery of praise by virtual agents and robots have not been methodically investigated previously. The team from the University of Tsukuba was determined to look into these questions in the new study.

Previous studies have shown that praise from others can positively affect offline improvements in human motor skills. However, whether praise from artificial beings can have similar effects on offline improvements has not been explored previously.

Masahiro Shiomi, Study First Author, University of Tsukuba

The team investigated these questions by asking participants to learn a finger-tapping task under many different conditions, which differed in terms of the frequency and timing of praise, the number of agents, and whether the agents were physically present or shown via a screen. Then, the participants were asked to repeat the function the next day, and performance for the two days was compared.

We found that praise led to a measurable increase in task performance, indicating increased offline consolidation of the task. Further, two agents led to significantly greater participant performance than one agent, even when the amount of praise was identical.

Takamasa Iio, Professor, University of Tsukuba

However, whether the praise was given by virtual agents or by physical robots did not impact the effects.

Our study showed that praise from artificial beings improved skill consolidation in a manner that resembled praise delivered by humans. Such findings may be useful for facilitating learning in children, for instance, or for exercise and rehabilitation applications.

Masahiro Shiomi, Study First Author, University of Tsukuba

Going forward, the researchers will explore the effects of praise given in various environments, for instance, in a VR setting, as well as the effects of higher numbers of agents.

A better understanding of the aspects that impact the social effects of robot behavior is vital for refining the quality of human-robot interactions, which are a highly crucial element of services, education, and entertainment applications.

Journal Reference:

Shiomi, M., et al. (2020) Two is better than one: Social rewards from two agents enhance offline improvements in motor skills more than single agent. PLOS ONE. doi.org/10.1371/journal.pone.0240622.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.