Researchers have used multi-agent reinforcement learning, a type of artificial intelligence (AI), to train multiple agents to work together in situations when communication lines are not open or are blocked.
Researchers say that when communication lines are open it is easier for agents to work together, but what they wanted to go after is decentralized way of working where communication channel is blocked. Scientists also focused on situations where it’s not obvious what the different roles or jobs for the agents should be. This particular scenario is much more complex and a harder problem because it’s not clear what one agent should do versus another agent.
Researchers used machine learning to solve this problem by creating a utility function that tells the agent when it is doing something useful or good for the team. They developed a machine learning technique that allowed them to identify when an individual agent contributes to the global team objective. If you look at it in terms of sports, one soccer player may score, but we also want to know about actions by other teammates that led to the goal, like assists. It’s hard to understand these delayed effects.
The algorithms the researchers developed can also identify when an agent or robot is doing something that doesn’t contribute to the goal. “It’s not so much the robot chose to do something wrong, just something that isn’t useful to the end goal”, said one of the researchers.
They tested their algorithms using simulated games like Capture the Flag and StarCraft, a popular computer game.
StarCraft can be a little bit more unpredictable and researchers were excited to see our method work well in this environment too.
Researchers said this type of algorithm is applicable to many real-life situations, such as military surveillance, robots working together in a warehouse, traffic signal control, autonomous vehicles coordinating deliveries, or controlling an electric power grid.