Cluster-Aware Attention-Based Deep Reinforcement Learning for Pickup and Delivery Problems

• URL: http://arxiv.org/abs/2603.10053v1
• Date: Mon, 09 Mar 2026 17:31:34 GMT
• Title: Cluster-Aware Attention-Based Deep Reinforcement Learning for Pickup and Delivery Problems
• Abstract summary: emphCAADRL (Cluster-Aware Attention-based Deep Reinforcement Learning) is a DRL framework that exploits the multi-scale structure of PDP instances.<n>Our method achieves these results with substantially lower inference time than neural collaborative-search baselines.
• Score: 6.977990610183958
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Pickup and Delivery Problem (PDP) is a fundamental and challenging variant of the Vehicle Routing Problem, characterized by tightly coupled pickup--delivery pairs, precedence constraints, and spatial layouts that often exhibit clustering. Existing deep reinforcement learning (DRL) approaches either model all nodes on a flat graph, relying on implicit learning to enforce constraints, or achieve strong performance through inference-time collaborative search at the cost of substantial latency. In this paper, we propose \emph{CAADRL} (Cluster-Aware Attention-based Deep Reinforcement Learning), a DRL framework that explicitly exploits the multi-scale structure of PDP instances via cluster-aware encoding and hierarchical decoding. The encoder builds on a Transformer and combines global self-attention with intra-cluster attention over depot, pickup, and delivery nodes, producing embeddings that are both globally informative and locally role-aware. Based on these embeddings, we introduce a Dynamic Dual-Decoder with a learnable gate that balances intra-cluster routing and inter-cluster transitions at each step. The policy is trained end-to-end with a POMO-style policy gradient scheme using multiple symmetric rollouts per instance. Experiments on synthetic clustered and uniform PDP benchmarks show that CAADRL matches or improves upon strong state-of-the-art baselines on clustered instances and remains highly competitive on uniform instances, particularly as problem size increases. Crucially, our method achieves these results with substantially lower inference time than neural collaborative-search baselines, suggesting that explicitly modeling cluster structure provides an effective and efficient inductive bias for neural PDP solvers.

Related papers

• From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network Control [17.40703988810448]
  This paper introduces a deployment-focused network control framework that addresses both obstacles.<n>First, we present Effective Congestion (EC), a deadline-aware metric family that quantifies interface congestion by packet urgency.<n>Second, we introduce a unified training objective that generalizes existing policy-learning paradigms.
  arXiv  Detail & Related papers  (2026-09-03T09:36:56Z)
• LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation [3.4535054007206636]
  Post-training large language models (LLMs) via reinforcement learning (RL) has significantly advanced code generation capabilities.<n>Current state-of-the-art frameworks leverage critic-free paradigms like Group Relative Policy Optimization (GRPO) tied to rule-based verification sandboxes.<n>We introduce LEAPLean Environment-Feedback via Adaptive Pruning, a scalable and computationally efficient multi-turn framework optimized for low-level hardware accelerator alignment.
  arXiv  Detail & Related papers  (2026-08-03T07:12:52Z)
• Multi-Agent DRL for V2X Resource Allocation: Disentangling Challenges and Benchmarking Solutions [51.22818149833102]
  Multi-agent reinforcement learning (MARL) has emerged as a promising approach for radio resource allocation in vehicle-to-everything (C-V2X) networks.<n>However, the multifaceted challenges inherent to MARL are often intertwined, making it difficult to understand their individual impact on performance in vehicular environments.<n>We bridge this gap by formulating C-V2X RRA as a sequence of multi-agent interference games with progressively increasing complexity.
  arXiv  Detail & Related papers  (2026-02-18T14:46:56Z)
• You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering [73.48306836608124]
  DCBoost is a parameter-free plug-in designed to enhance the global feature structures of current deep clustering models.<n>By harnessing reliable local structural cues, our method aims to elevate clustering performance effectively.
  arXiv  Detail & Related papers  (2025-11-26T09:16:36Z)
• An End-to-End Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with Drones [12.385878815004283]
  This study proposes a hierarchical Actor-Critic deep reinforcement learning framework for solving the Traveling Salesman Problem with Drones (TSP-D)<n>The architecture consists of two primary computation: a Transformer-inspired encoder and an efficient Minimal Gated Unit decoder.<n>The entire framework operates within an asynchronous advantage actor-critic paradigm.
  arXiv  Detail & Related papers  (2025-11-07T14:26:29Z)
• Design Optimization of NOMA Aided Multi-STAR-RIS for Indoor Environments: A Convex Approximation Imitated Reinforcement Learning Approach [51.63921041249406]
  Non-orthogonal multiple access (NOMA) enables multiple users to share the same frequency band, and simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) deploying STAR-RIS indoors presents challenges in interference mitigation, power consumption, and real-time configuration. A novel network architecture utilizing multiple access points (APs), STAR-RISs, and NOMA is proposed for indoor communication.
  arXiv  Detail & Related papers  (2024-06-19T07:17:04Z)
• Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment [58.049113055986375]
  We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy.<n>The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms.<n>We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
  arXiv  Detail & Related papers  (2024-06-11T01:20:53Z)
• GASE: Graph Attention Sampling with Edges Fusion for Solving Vehicle Routing Problems [6.084414764415137]
  We propose an adaptive Graph Attention Sampling with the Edges Fusion framework to solve vehicle routing problems. Our proposed model outperforms the existing methods by 2.08%-6.23% and shows stronger generalization ability.
  arXiv  Detail & Related papers  (2024-05-21T03:33:07Z)
• Towards Lightweight Cross-domain Sequential Recommendation via External Attention-enhanced Graph Convolution Network [7.1102362215550725]
  Cross-domain Sequential Recommendation (CSR) depicts the evolution of behavior patterns for overlapped users by modeling their interactions from multiple domains. We introduce a lightweight external attention-enhanced GCN-based framework to solve the above challenges, namely LEA-GCN. To further alleviate the framework structure and aggregate the user-specific sequential pattern, we devise a novel dual-channel External Attention (EA) component.
  arXiv  Detail & Related papers  (2023-02-07T03:06:29Z)
• COMET: A Comprehensive Cluster Design Methodology for Distributed Deep Learning Training [42.514897110537596]
  Modern Deep Learning (DL) models have grown to sizes requiring massive clusters of specialized, high-end nodes to train. designing such clusters to maximize both performance and utilization--to amortize their steep cost--is a challenging task. We introduce COMET, a holistic cluster design methodology and workflow to jointly study the impact of parallelization strategies and key cluster resource provisioning on the performance of distributed DL training.
  arXiv  Detail & Related papers  (2022-11-30T00:32:37Z)
• Deep clustering with fusion autoencoder [0.0]
  Deep clustering (DC) models capitalize on autoencoders to learn intrinsic features which facilitate the clustering process in consequence. In this paper, a novel DC method is proposed to address this issue. Specifically, the generative adversarial network and VAE are coalesced into a new autoencoder called fusion autoencoder (FAE)
  arXiv  Detail & Related papers  (2022-01-11T07:38:03Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• Deep Attention-guided Graph Clustering with Dual Self-supervision [49.040136530379094]
  We propose a novel method, namely deep attention-guided graph clustering with dual self-supervision (DAGC) We develop a dual self-supervision solution consisting of a soft self-supervision strategy with a triplet Kullback-Leibler divergence loss and a hard self-supervision strategy with a pseudo supervision loss. Our method consistently outperforms state-of-the-art methods on six benchmark datasets.
  arXiv  Detail & Related papers  (2021-11-10T06:53:03Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.