In this video, we will seek some motivation for why we should consider multiple agents in the context of Artificial Intelligence. Keep in mind that the ultimate goal of AI is to solve intelligence. We live in a multi agent world, we do not become intelligent in isolation. As a baby, the closest interactions that shape us are with our parents. In school, we learn to collaborate and compete with others. We try to predict what might surprise our friends for their birthdays. We learn from others, and our own experiences, and so on. Our intelligence is therefore a result of our interactions with multiple agents over our lifetime. If we want to build intelligent agents that are used in the real world, they have to interact with humans, which are just another agent, and also with other agents. This leads to a multi-agent scenario. If we really want to solve the problem of intelligence, our agents should be able to achieve their goals in very complex environments. The multi-agent case is a very complex kind of environment because all the agents are learning simultaneously and also interacting with one another. Just like we have in real life, there are different kinds of interactions going on between agents, from coordination to competition, to communication, to prediction, negotiation, and so on. All these facts motivate us to expand our horizon from single agents to multiple agents.