A Multiphase Semistatic Training Method for Swarm Confrontation Using Multiagent Deep Reinforcement Learning

<div>Intelligent behaviors of tanks in the confrontation. (a) Front and rear double-team (b) Go around behind the enemy and attack. (c) Besiege the minority by the majority (d) Luring the enemy to create attack opportunities for teammates.</div>

Computational Intelligence and Neuroscience

fig4

Figure 4

Figure 4: A Multiphase Semistatic Training Method for Swarm Confrontation Using Multiagent Deep Reinforcement Learning 