The players can cooperate to achieve an objective, and compete against other players with conflicting interests. Creating artificial intelligence agents that can learn to compete and cooperate as effectively as humans remains a thorny problem. A key challenge is enabling AI agents to anticipate future behaviors of other agents when they are all learning simultaneously. Because of the complexity of this problem, current approaches tend to be myopic; the agents can only guess the next few moves of their teammates or competitors, which leads to poor performance in the long run. Researchers from MIT, the MIT-IBM Watson AI Lab, and elsewhere have developed a new approach that gives AI agents a farsighted perspective.

New system can teach a group of cooperative or competitive AI agents to find an optimal long-term solution.

The players can cooperate to achieve an objective, and compete against other players with conflicting interests. Creating artificial intelligence agents that can learn to compete and cooperate as effectively as humans remains a thorny problem. A key challenge is enabling AI agents to anticipate future behaviors of other agents when they are all learning simultaneously. Because of the complexity of this problem, current approaches tend to be myopic; the agents can only guess the next few moves of their teammates or competitors, which leads to poor performance in the long run. Researchers from MIT, the MIT-IBM Watson AI Lab, and elsewhere have developed a new approach that gives AI agents a farsighted perspective.