Partially Observable Learning for Multi-Platform Dispatch Optimization

• URL: http://arxiv.org/abs/2608.10897v1
• Date: Tue, 11 Aug 2026 13:20:12 GMT
• Title: Partially Observable Learning for Multi-Platform Dispatch Optimization
• Abstract summary: In real-world systems, couriers are not exclusive to a single platform and may concurrently serve multiple platforms.<n>This results in a multi-platform dispatch environment with inherent partial observability.<n>We propose POLO, a partially observable multi-agent reinforcement learning framework for dispatching optimization in multi-platform instant delivery systems.
• Score: 2.877073407903913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instant delivery platforms have become a critical component of urban logistics, increasingly relying on crowdsourced couriers to fulfill highly dynamic orders. In real-world systems, couriers are not exclusive to a single platform and may concurrently serve multiple platforms, while each platform can only observe its own orders and couriers' interactions due to privacy and operational constraints. This results in a multi-platform dispatch environment with inherent partial observability. However, most existing works on dispatch optimization assume full courier observability and mandatory assignment acceptance, causing substantial performance degradation when deployed in realistic multi-platform settings. In this paper, we propose POLO, a partially observable multi-agent reinforcement learning framework for dispatching optimization in multi-platform instant delivery systems. POLO firstly models each platform-grid pair as an independent agent that learns dispatch policies solely from platform-local observations, aligning the learning process with real-world privacy and operational constraints. To support effective decision-making under incomplete and heterogeneous courier information, POLO introduces a novel attention-based policy representation that selectively aggregates inter-courier information. Moreover, we design a counterfactual reward shaping mechanism to mitigate the non-stationarity induced by joint actions across grids, leading to more stable and scalable learning. We develop a high-fidelity simulator to evaluate dispatch performance under varying numbers of platforms and system scales. Extensive experiments demonstrate that POLO consistently outperforms strong baselines in terms of platform revenue and courier travel efficiency, highlighting its robustness and effectiveness in realistic multi-platform settings.

Related papers

• UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning [67.45909103605858]
  We propose UI-MOPD, a method that incorporates multi-teacher on-policy distillation into continual learning for GUI agents.<n>Experiments on OSWorld and MobileWorld show that UI-MOPD achieves task success rates of 38.2% and 12.0%, respectively.
  arXiv  Detail & Related papers  (2026-07-05T17:37:12Z)
• Cross-Platform Control for Autonomous Surface Vehicles via Adaptive Reinforcement Learning [3.8494315501944736]
  We present an adaptive reinforcement learning approach for trajectory tracking that enables zero-shot cross-platform deployment.<n>The policy is trained in simulation under randomized vessel dynamics and is deployed zero-shot to two real-world platforms without any fine-tuning.<n>In real-world experiments on two different platforms, the adaptive policy outperforms non-adaptive learning-based baselines by up to 58% in position mean absolute error.
  arXiv  Detail & Related papers  (2026-07-02T11:04:21Z)
• FedLLM: A Privacy-Preserving Federated Large Language Model for Explainable Traffic Flow Prediction [1.2043574473965315]
  This study proposes FedLLM, a privacy- and distributed framework for explainable multi-horizon short-term traffic flow prediction.<n>FedLLM allows each client to learn from local traffic patterns while contributing to a shared global model.<n> Experimental results show that FedLLM achieves improved predictive performance over centralized baselines.
  arXiv  Detail & Related papers  (2026-04-17T18:09:44Z)
• LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms [12.693132563364342]
  Short-video platforms are closed-loop, human-in-the-loop ecosystems where policy, creator incentives, and user behavior co-evolve.<n>We propose a large language model (LLM)-augmented digital twin for short-video platforms with a modular four-twin architecture.
  arXiv  Detail & Related papers  (2026-03-11T21:50:21Z)
• SOP: A Scalable Online Post-Training System for Vision-Language-Action Models [15.86316960521611]
  Vision-language-action (VLA) models achieve strong generalization through large-scale pre-training, but real-world deployment requires expert-level task proficiency in addition to broad generality.<n>Existing post-training approaches for VLA models are typically offline, single-robot, or task-specific.<n>We introduce a Scalable Online Post-training system that enables online, distributed, multi-task post-training of generalist VLA models directly in the physical world.
  arXiv  Detail & Related papers  (2026-01-06T14:25:11Z)
• Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems [75.78934957242403]
  Self-driving vehicles and drones require true Spatial Intelligence from multi-modal onboard sensor data.<n>This paper presents a framework for multi-modal pre-training, identifying the core set of techniques driving progress toward this goal.
  arXiv  Detail & Related papers  (2025-12-30T17:58:01Z)
• Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only [70.43369087819332]
  Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models with human-annotated demonstrations.<n>We propose Self-Rewarding PPO, a novel fine-tuning method that leverages on-policy techniques to enhance generalization performance.
  arXiv  Detail & Related papers  (2025-10-24T02:02:13Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• In-the-Flow Agentic System Optimization for Effective Planning and Tool Use [73.72524040856052]
  AgentFlow is a trainable, in-the-flow agentic framework that coordinates four modules (planner, executor, verifier, generator) through an evolving memory.<n>Flow-GRPO tackles long-horizon, sparse-reward credit assignment by converting multi-turn optimization into a sequence of tractable single-turn policy updates.<n>AgentFlow with a 7B-scale backbone outperforms top-performing baselines with average accuracy gains of 14.9% on search, 14.0% on agentic, 14.5% on mathematical, and 4.1% on scientific tasks.
  arXiv  Detail & Related papers  (2025-10-07T05:32:44Z)
• FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models [56.31350619667909]
  Federated prompt learning (FPL) for vision-language models is a powerful approach to collaboratively adapt models across distributed clients.<n>Existing FPL approaches suffer from a trade-off between performance and robustness, particularly in out-of-distribution (OOD) shifts.<n>We introduce a Federated OOD-aware Context Optimization (FOCoOp) framework, which captures diverse distributions among clients.
  arXiv  Detail & Related papers  (2025-06-19T11:16:02Z)
• Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies.<n>Our findings are synthesized in Flex (Fly lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors.<n>We demonstrate the effectiveness of this approach on a quadrotor fly-to-target task, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• Harvesting Efficient On-Demand Order Pooling from Skilled Couriers: Enhancing Graph Representation Learning for Refining Real-time Many-to-One Assignments [11.0829498096027]
  On-demand food delivery (OFD) services offer delivery fulfillment within dozens of minutes after an order is placed. In OFD, pooling multiple orders for simultaneous delivery in real-time order assignment is a pivotal efficiency source. The complexity and real-time nature of order assignment, making extensive calculations impractical, significantly limit the potential for order consolidation. A SC delivery network (SCDN) is constructed, based on an enhanced attributed heterogeneous network embedding approach tailored for OFD.
  arXiv  Detail & Related papers  (2024-06-20T18:03:27Z)

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.