Measuring collaborative emergent behavior in multi-agent reinforcement learning

Understand

Multi-agent reinforcement learning (RL) has important implications for the future of human-agent teaming.

• We show that improved performance with multi-agent RL is not a guarantee of the collaborative behavior thought to be important for solving multi-agent tasks.
• To address this, we present a novel approach for quantitatively assessing collaboration in continuous spatial tasks with multi-agent RL.
• Such a metric is useful for measuring collaboration between computational agents and may serve as a training signal for collaboration in future RL paradigms involving humans.