Last night as I was trying to sleep, I was thinking about robots and how they would operate in the future. I had wondered how robots would work with us but more importantly, how robots would work with each other because many robots may be built by different companies and may not be on the same communication line. After sleeping on it, I did some research the next day and came across a new article written by UIUC that spoke almost exactly to my curiosity. A few researchers at the Grainger College of Engineering developed a sort of artificial intelligence that used “multi-agent reinforcement learning”, a term that I have not heard of before. After diving deeper into it, the machine basically learns from its past experiences and builds a training method that rewards and punishes certain decisions made by the machine.
One of the researchers made an interesting analogy that resonated with me. He mentioned that he wanted the robots to not just look at the main action at hand but the actions that are done before and after the main action, like an assist when scoring a goal in soccer. I found this really interesting because it can help someone's mind wrap around how this type of AI works and how the robot is not always looking for right and wrong but for actions that are unnecessary in the big picture.
I really like this form of AI because it helps keep the purpose of the machine flexible as it can really be anything in any environment and it can learn from its surroundings to work with the other robots in the area without having to actually communicate with them. For example, in the autonomous vehicle industry, in another 5–10 years, there will be a handful of different companies building self-driving cars and for them to work with other cars on the road to minimalize the chance of an accident, they can implement this kind of AI so it does not have to necessarily communicate with third-party companies but it makes traffic a bit easier when the vehicles can ‘talk’ to each other.
All in all, I continue to find AI to be an interesting field that continues to amaze me every day as the field is still new and ever-growing.
BTW: If you want the original link I found, here it is: https://aerospace.illinois.edu/news/49234
