Deep Learning Agents Trained For Avoidance Behave Like Hawks And Doves
This work addresses coordination and avoidance strategies in multi-agent systems, but it is incremental as it applies existing deep learning methods to a simple game scenario.
The study tackled the problem of training deep learning agents in a symmetrical grid world to cross paths without collisions, finding that the fully trained network exhibited behavior analogous to the Hawks and Doves game, with one agent adopting an aggressive strategy and the other learning to avoid it.
We present heuristically optimal strategies expressed by deep learning agents playing a simple avoidance game. We analyse the learning and behaviour of two agents within a symmetrical grid world that must cross paths to reach a target destination without crashing into each other or straying off of the grid world in the wrong direction. The agent policy is determined by one neural network that is employed in both agents. Our findings indicate that the fully trained network exhibits behaviour similar to that of the game Hawks and Doves, in that one agent employs an aggressive strategy to reach the target while the other learns how to avoid the aggressive agent.