Few-Shot Learning for Dynamic Operations of Automated Electric Taxi Fleets under Evolving Charging Infrastructure: A Meta-Deep Reinforcement Learning Approach

TL;DR

This paper introduces GAT-PEARL, a meta-reinforcement learning framework that enables autonomous electric taxi fleets to adapt efficiently to evolving charging infrastructure using graph attention networks and probabilistic embeddings.

Contribution

It presents a novel combination of graph attention networks and probabilistic embeddings within a meta-reinforcement learning framework for adaptive fleet management.

Findings

GAT-PEARL outperforms traditional RL methods in simulations.

It generalizes well to unseen infrastructure layouts.

It improves operational efficiency in dynamic environments.

Abstract

With the rapid expansion of electric vehicles (EVs) and charging infrastructure, the effective management of Autonomous Electric Taxi (AET) fleets faces a critical challenge in environments with dynamic and uncertain charging availability. While most existing research assumes a static charging network, this simplification creates a significant gap between theoretical models and real-world operations. To bridge this gap, we propose GAT-PEARL, a novel meta-reinforcement learning framework that learns an adaptive operational policy. Our approach integrates a graph attention network (GAT) to effectively extract robust spatial representations under infrastructure layouts and model the complex spatiotemporal relationships of the urban environment, and employs probabilistic embeddings for actor-critic reinforcement learning (PEARL) to enable rapid, inference-based adaptation to changes in charging network layouts without retraining. Through extensive simulations on real-world data in Chengdu, China, we demonstrate that GAT-PEARL significantly outperforms conventional reinforcement learning baselines, showing superior generalization to unseen infrastructure layouts and achieving higher overall operational efficiency in dynamic settings.