MAexp: A Generic Platform for RL-based Multi-Agent Exploration

TL;DR

MAexp is a versatile platform for multi-agent exploration in robotics that integrates advanced MARL algorithms, uses point clouds for high-fidelity mapping, and offers a fast, scalable environment for benchmarking diverse algorithms.

Contribution

It introduces MAexp, a comprehensive platform combining multiple MARL algorithms, high-fidelity environment modeling, and scalable multi-robot support for exploration tasks.

Findings

Point cloud-based scenarios enable high-fidelity mapping.

Sampling speed is approximately 40 times faster than existing platforms.

Benchmark results highlight strengths of various MARL algorithms across scenarios.

Abstract

The sim-to-real gap poses a significant challenge in RL-based multi-agent exploration due to scene quantization and action discretization. Existing platforms suffer from the inefficiency in sampling and the lack of diversity in Multi-Agent Reinforcement Learning (MARL) algorithms across different scenarios, restraining their widespread applications. To fill these gaps, we propose MAexp, a generic platform for multi-agent exploration that integrates a broad range of state-of-the-art MARL algorithms and representative scenarios. Moreover, we employ point clouds to represent our exploration scenarios, leading to high-fidelity environment mapping and a sampling speed approximately 40 times faster than existing platforms. Furthermore, equipped with an attention-based Multi-Agent Target Generator and a Single-Agent Motion Planner, MAexp can work with arbitrary numbers of agents and accommodate various types of robots. Extensive experiments are conducted to establish the first benchmark featuring several high-performance MARL algorithms across typical scenarios for robots with continuous actions, which highlights the distinct strengths of each algorithm in different scenarios.