Fluid-Agent Reinforcement Learning
This addresses the limitation of fixed-agent populations in MARL for real-world applications where agent numbers are fluid, offering a novel framework for dynamic agent creation.
The paper tackles the problem of multi-agent reinforcement learning with a dynamic number of agents, proposing a fluid-agent framework where agents can create others. It shows that this approach enables agent teams to adjust their size dynamically to match environmental demands, as demonstrated in benchmarks like Predator-Prey and Level-Based Foraging.
The primary focus of multi-agent reinforcement learning (MARL) has been to study interactions among a fixed number of agents embedded in an environment. However, in the real world, the number of agents is neither fixed nor known a priori. Moreover, an agent can decide to create other agents (for example, a cell may divide, or a company may spin off a division). In this paper, we propose a framework that allows agents to create other agents; we call this a fluid-agent environment. We present game-theoretic solution concepts for fluid-agent games and empirically evaluate the performance of several MARL algorithms within this framework. Our experiments include fluid variants of established benchmarks such as Predator-Prey and Level-Based Foraging, where agents can dynamically spawn, as well as a new environment we introduce that highlights how fluidity can unlock novel solution strategies beyond those observed in fixed-population settings. We demonstrate that this framework yields agent teams that adjust their size dynamically to match environmental demands.