In our multi-agent approach, the player positions itself flexibly such that it anticipates that it will be useful to the team, either offensively or defensively.
Two ways in which agents can use the position flexibility is to react to the ball's position and to mark opponents. When reacting to the ball's position, the agent moves to a location within its range that minimizes its distance to the ball. When marking opponents, agents move next to a given opponent rather than staying at the default position home. The opponent to mark can be chosen by the player (e.g., the closest opponent), or by the unit captain which can ensure that all opponents are marked, following a preset algorithm as part of the locker-room agreement.
As emphasized throughout, homogeneous agents can play different positions. But such a capability raises the challenging issue of when the players should change positions. In addition, with teammates switching positions, a player's internal player-position map could become incorrect and/or incomplete. The locker-room agreement provides procedures to the team that allow for coordinated role changing. In our case, the locker-room agreement designates an order of precedence switching among positions within each unit. When a high-priority position is left vacant, players currently filling lower-priority positions consider switching to the recently vacated position. If a player detects that another player is trying to fill the same role, it either vacates the position or informs the other player of the conflict depending on which player is closer to the position's home coordinates.
By switching positions within a formation, the overall joint performance of the team is improved. Position-switching saves player energy and allows them to respond more quickly to the ball.