Their findings suggest that cooperative hunting, previously thought to be a complex social behavior seen primarily in mammals such as lions and chimpanzees, can also develop in species with lower levels of cognitive ability.
To investigate this puzzle, Tsutsui and his collaborators created a computational model in which AI agents learn to hunt together, using deep reinforcement learning. Deep reinforcement learning is a process in which behaviors are reinforced by being rewarded after performing them. Researchers train algorithms to learn through interaction with the environment and receiving rewards for specific actions.
During the simulations, the AI predators exhibited distinct and complementary roles, similar to the behavior of animals that engage in cooperative hunting. For example, one agent would chase the prey, while another would ambush it. As the number of predators increased, the success rate increased, and the time required for hunts decreased.
"Our predator agents learned to collaborate using reinforcement learning, without requiring complex cognitive mechanisms akin to theory of mind," Tsutsui said."This suggests that cooperative hunting can evolve in a wider range of species than previously thought."