Fluid-Agent Reinforcement Learning

TL;DR

This paper introduces a fluid-agent reinforcement learning framework where agents can dynamically create or remove agents, enabling adaptive team sizes and new strategies in multi-agent systems.

Contribution

It proposes a novel fluid-agent environment framework with game-theoretic solutions and demonstrates its effectiveness through empirical evaluations on modified benchmarks.

Findings

Agents can dynamically adjust team sizes in response to environment

Fluid-agent framework enables novel solution strategies

Improved performance on fluid variants of benchmarks

Abstract

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.