TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning

TL;DR

TABX is a high-throughput, customizable sandbox environment built with JAX that accelerates multi-agent reinforcement learning research by enabling extensive parallelization and flexible scenario design.

Contribution

We introduce TABX, a modular, GPU-accelerated sandbox for MARL that allows detailed environmental control and scalable experimentation.

Findings

Enables massive parallelization of MARL experiments.

Reduces computational overhead significantly.

Provides a flexible platform for complex multi-agent tasks.

Abstract

The design of environments plays a critical role in shaping the development and evaluation of cooperative multi-agent reinforcement learning (MARL) algorithms. While existing benchmarks highlight critical challenges, they often lack the modularity required to design custom evaluation scenarios. We introduce the Totally Accelerated Battle Simulator in JAX (TABX), a high-throughput sandbox designed for reconfigurable multi-agent tasks. TABX provides granular control over environmental parameters, permitting a systematic investigation into emergent agent behaviors and algorithmic trade-offs across a diverse spectrum of task complexities. Leveraging JAX for hardware-accelerated execution on GPUs, TABX enables massive parallelization and significantly reduces computational overhead. By providing a fast, extensible, and easily customized framework, TABX facilitates the study of MARL agents in complex structured domains and serves as a scalable foundation for future research. Our code is available at: https://anonymous.4open.science/r/TABX-00CA.