Researchers at the US Army Research Laboratory and the University of Texas at Austin considered a specific case where a human provides real time feedback in the form of critique.
First introduced by researchers as training an agent manually via Evaluative Reinforcement (TAMER), the team developed a new algorithm called deep TAMER.
Many current techniques in AI require robots to interact with their environment for extended periods of time to learn how to optimally per form a task.
It is an extension of TAMER that uses deep 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.
Within the next one to two years, researchers are interested in exploring the applicability of their newest technique in a wider variety of environments, like video games other than Atari Bowling and additional simulation environments.
The team considered situations where a human teaches how to behave by observing it and providing critique, like "good job" or "bad job".
Comments
Post a Comment