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

arXiv:2404.12824v1 Announce Type: cross
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 …

abstract agent algorithms applications arxiv challenge cs.lg cs.ma cs.ro diversity exploration gap multi-agent platform platforms quantization reinforcement reinforcement learning sampling sim type