Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task Planning

TL;DR

This paper introduces a scalable hierarchical reinforcement learning framework for multi-robot task planning in large-scale warehouse systems, achieving high performance and generalization in complex, dynamic environments.

Contribution

It develops a multi-stage HRL-based planner with a hierarchical temporal attention network and curricula, enhancing scalability and generalization for hyper scale multi-robot task planning.

Findings

Outperforms state-of-the-art methods in simulated and real-world RMFS.

Successfully scales to 200 robots and 1000 racks on unseen maps.

Maintains high performance across various unlearned environments.

Abstract

To improve the efficiency of warehousing system and meet huge customer orders, we aim to solve the challenges of dimension disaster and dynamic properties in hyper scale multi-robot task planning (MRTP) for robotic mobile fulfillment system (RMFS). Existing research indicates that hierarchical reinforcement learning (HRL) is an effective method to reduce these challenges. Based on that, we construct an efficient multi-stage HRL-based multi-robot task planner for hyper scale MRTP in RMFS, and the planning process is represented with a special temporal graph topology. To ensure optimality, the planner is designed with a centralized architecture, but it also brings the challenges of scaling up and generalization that require policies to maintain performance for various unlearned scales and maps. To tackle these difficulties, we first construct a hierarchical temporal attention network (HTAN) to ensure basic ability of handling inputs with unfixed lengths, and then design multi-stage curricula for hierarchical policy learning to further improve the scaling up and generalization ability while avoiding catastrophic forgetting. Additionally, we notice that policies with hierarchical structure suffer from unfair credit assignment that is similar to that in multi-agent reinforcement learning, inspired of which, we propose a hierarchical reinforcement learning algorithm with counterfactual rollout baseline to improve learning performance. Experimental results demonstrate that our planner outperform other state-of-the-art methods on various MRTP instances in both simulated and real-world RMFS. Also, our planner can successfully scale up to hyper scale MRTP instances in RMFS with up to 200 robots and 1000 retrieval racks on unlearned maps while keeping superior performance over other methods.