Haoyuan Hu

Xiaowei Mao, Haomin Wen, Hengrui Zhang et al.

Pick-up and Delivery Route Prediction (PDRP), which aims to estimate the future service route of a worker given his current task pool, has received rising attention in recent years. Deep neural networks based on supervised learning have emerged as the dominant model for the task because of their powerful ability to capture workers' behavior patterns from massive historical data. Though promising, they fail to introduce the non-differentiable test criteria into the training process, leading to a mismatch in training and test criteria. Which considerably trims down their performance when applied in practical systems. To tackle the above issue, we present the first attempt to generalize Reinforcement Learning (RL) to the route prediction task, leading to a novel RL-based framework called DRL4Route. It combines the behavior-learning abilities of previous deep learning models with the non-differentiable objective optimization ability of reinforcement learning. DRL4Route can serve as a plug-and-play component to boost the existing deep learning models. Based on the framework, we further implement a model named DRL4Route-GAE for PDRP in logistic service. It follows the actor-critic architecture which is equipped with a Generalized Advantage Estimator that can balance the bias and variance of the policy gradient estimates, thus achieving a more optimal policy. Extensive offline experiments and the online deployment show that DRL4Route-GAE improves Location Square Deviation (LSD) by 0.9%-2.7%, and Accuracy@3 (ACC@3) by 2.4%-3.2% over existing methods on the real-world dataset.

Youfang Lin, Jinji Fu, Haomin Wen et al.

In Location-Based Services (LBS), such as food delivery, a fundamental task is segmenting Areas of Interest (AOIs), aiming at partitioning the urban geographical spaces into non-overlapping regions. Traditional AOI segmentation algorithms primarily rely on road networks to partition urban areas. While promising in modeling the geo-semantics, road network-based models overlooked the service-semantic goals (e.g., workload equality) in LBS service. In this paper, we point out that the AOI segmentation problem can be naturally formulated as a Markov Decision Process (MDP), which gradually chooses a nearby AOI for each grid in the current AOI's border. Based on the MDP, we present the first attempt to generalize Deep Reinforcement Learning (DRL) for AOI segmentation, leading to a novel DRL-based framework called DRL4AOI. The DRL4AOI framework introduces different service-semantic goals in a flexible way by treating them as rewards that guide the AOI generation. To evaluate the effectiveness of DRL4AOI, we develop and release an AOI segmentation system. We also present a representative implementation of DRL4AOI - TrajRL4AOI - for AOI segmentation in the logistics service. It introduces a Double Deep Q-learning Network (DDQN) to gradually optimize the AOI generation for two specific semantic goals: i) trajectory modularity, i.e., maximize tightness of the trajectory connections within an AOI and the sparsity of connections between AOIs, ii) matchness with the road network, i.e., maximizing the matchness between AOIs and the road network. Quantitative and qualitative experiments conducted on synthetic and real-world data demonstrate the effectiveness and superiority of our method. The code and system is publicly available at https://github.com/Kogler7/AoiOpt.

Hexian Ni, Tao Lu, Haoyuan Hu et al.

Preference-based Reinforcement Learning (PbRL) methods provide a solution to avoid reward engineering by learning reward models based on human preferences. However, poor feedback- and sample- efficiency still remain the problems that hinder the application of PbRL. In this paper, we present a novel efficient query selection and preference-guided exploration method, called SENIOR, which could select the meaningful and easy-to-comparison behavior segment pairs to improve human feedback-efficiency and accelerate policy learning with the designed preference-guided intrinsic rewards. Our key idea is twofold: (1) We designed a Motion-Distinction-based Selection scheme (MDS). It selects segment pairs with apparent motion and different directions through kernel density estimation of states, which is more task-related and easy for human preference labeling; (2) We proposed a novel preference-guided exploration method (PGE). It encourages the exploration towards the states with high preference and low visits and continuously guides the agent achieving the valuable samples. The synergy between the two mechanisms could significantly accelerate the progress of reward and policy learning. Our experiments show that SENIOR outperforms other five existing methods in both human feedback-efficiency and policy convergence speed on six complex robot manipulation tasks from simulation and four real-worlds.

Hao Zeng, Jiaqi Wang, Avirup Das et al.

Feasible solutions are crucial for Integer Programming (IP) since they can substantially speed up the solving process. In many applications, similar IP instances often exhibit similar structures and shared solution distributions, which can be potentially modeled by deep learning methods. Unfortunately, existing deep-learning-based algorithms, such as Neural Diving and Predict-and-search framework, are limited to generating only partial feasible solutions, and they must rely on solvers like SCIP and Gurobi to complete the solutions for a given IP problem. In this paper, we propose a novel framework that generates complete feasible solutions end-to-end. Our framework leverages contrastive learning to characterize the relationship between IP instances and solutions, and learns latent embeddings for both IP instances and their solutions. Further, the framework employs diffusion models to learn the distribution of solution embeddings conditioned on IP representations, with a dedicated guided sampling strategy that accounts for both constraints and objectives. We empirically evaluate our framework on four typical datasets of IP problems, and show that it effectively generates complete feasible solutions with a high probability (> 89.7 \%) without the reliance of Solvers and the quality of solutions is comparable to the best heuristic solutions from Gurobi. Furthermore, by integrating our method's sampled partial solutions with the CompleteSol heuristic from SCIP, the resulting feasible solutions outperform those from state-of-the-art methods across all datasets, exhibiting a 3.7 to 33.7\% improvement in the gap to optimal values, and maintaining a feasible ratio of over 99.7\% for all datasets.

Lu Duan, Haoyuan Hu, Zili Wu et al.

Balanced order batching problem (BOBP) arises from the process of warehouse picking in Cainiao, the largest logistics platform in China. Batching orders together in the picking process to form a single picking route, reduces travel distance. The reason for its importance is that order picking is a labor intensive process and, by using good batching methods, substantial savings can be obtained. The BOBP is a NP-hard combinational optimization problem and designing a good problem-specific heuristic under the quasi-real-time system response requirement is non-trivial. In this paper, rather than designing heuristics, we propose an end-to-end learning and optimization framework named Balanced Task-orientated Graph Clustering Network (BTOGCN) to solve the BOBP by reducing it to balanced graph clustering optimization problem. In BTOGCN, a task-oriented estimator network is introduced to guide the type-aware heterogeneous graph clustering networks to find a better clustering result related to the BOBP objective. Through comprehensive experiments on single-graph and multi-graphs, we show: 1) our balanced task-oriented graph clustering network can directly utilize the guidance of target signal and outperforms the two-stage deep embedding and deep clustering method; 2) our method obtains an average 4.57m and 0.13m picking distance ("m" is the abbreviation of the meter (the SI base unit of length)) reduction than the expert-designed algorithm on single and multi-graph set and has a good generalization ability to apply in practical scenario.

Yujie Chen, Yu Qian, Yichen Yao et al.

In this paper, we study a courier dispatching problem (CDP) raised from an online pickup-service platform of Alibaba. The CDP aims to assign a set of couriers to serve pickup requests with stochastic spatial and temporal arrival rate among urban regions. The objective is to maximize the revenue of served requests given a limited number of couriers over a period of time. Many online algorithms such as dynamic matching and vehicle routing strategy from existing literature could be applied to tackle this problem. However, these methods rely on appropriately predefined optimization objectives at each decision point, which is hard in dynamic situations. This paper formulates the CDP as a Markov decision process (MDP) and proposes a data-driven approach to derive the optimal dispatching rule-set under different scenarios. Our method stacks multi-layer images of the spatial-and-temporal map and apply multi-agent reinforcement learning (MARL) techniques to evolve dispatching models. This method solves the learning inefficiency caused by traditional centralized MDP modeling. Through comprehensive experiments on both artificial dataset and real-world dataset, we show: 1) By utilizing historical data and considering long-term revenue gains, MARL achieves better performance than myopic online algorithms; 2) MARL is able to construct the mapping between complex scenarios to sophisticated decisions such as the dispatching rule. 3) MARL has the scalability to adopt in large-scale real-world scenarios.

Yiheng Zhu, Yichen Yao, Zili Wu et al.

Convolutional neural networks (CNNs) are effective at solving difficult problems like visual recognition, speech recognition and natural language processing. However, performance gain comes at the cost of laborious trial-and-error in designing deeper CNN architectures. In this paper, a genetic programming (GP) framework for convolutional neural network architecture search, abbreviated as GP-CNAS, is proposed to automatically search for optimal CNN architectures. GP-CNAS encodes CNNs as trees where leaf nodes (GP terminals) are selected residual blocks and non-leaf nodes (GP functions) specify the block assembling procedure. Our tree-based representation enables easy design and flexible implementation of genetic operators. Specifically, we design a dynamic crossover operator that strikes a balance between exploration and exploitation, which emphasizes CNN complexity at early stage and CNN diversity at later stage. Therefore, the desired CNN architecture with balanced depth and width can be found within limited trials. Moreover, our GP-CNAS framework is highly compatible with other manually-designed and NAS-generated block types as well. Experimental results on the CIFAR-10 dataset show that GP-CNAS is competitive among the state-of-the-art automatic and semi-automatic NAS algorithms.

Lu Duan, Haoyuan Hu, Yu Qian et al.

A 3D flexible bin packing problem (3D-FBPP) arises from the process of warehouse packing in e-commerce. An online customer's order usually contains several items and needs to be packed as a whole before shipping. In particular, 5% of tens of millions of packages are using plastic wrapping as outer packaging every day, which brings pressure on the plastic surface minimization to save traditional logistics costs. Because of the huge practical significance, we focus on the issue of packing cuboid-shaped items orthogonally into a least-surface-area bin. The existing heuristic methods for classic 3D bin packing don't work well for this particular NP-hard problem and designing a good problem-specific heuristic is non-trivial. In this paper, rather than designing heuristics, we propose a novel multi-task framework based on Selected Learning to learn a heuristic-like policy that generates the sequence and orientations of items to be packed simultaneously. Through comprehensive experiments on a large scale real-world transaction order dataset and online AB tests, we show: 1) our selected learning method trades off the imbalance and correlation among the tasks and significantly outperforms the single task Pointer Network and the multi-task network without selected learning; 2) our method obtains an average 5.47% cost reduction than the well-designed greedy algorithm which is previously used in our online production system.

Haoyuan Hu, Xiaodong Zhang, Xiaowei Yan et al.

In this paper, a new type of 3D bin packing problem (BPP) is proposed, in which a number of cuboid-shaped items must be put into a bin one by one orthogonally. The objective is to find a way to place these items that can minimize the surface area of the bin. This problem is based on the fact that there is no fixed-sized bin in many real business scenarios and the cost of a bin is proportional to its surface area. Our research shows that this problem is NP-hard. Based on previous research on 3D BPP, the surface area is determined by the sequence, spatial locations and orientations of items. Among these factors, the sequence of items plays a key role in minimizing the surface area. Inspired by recent achievements of deep reinforcement learning (DRL) techniques, especially Pointer Network, on combinatorial optimization problems such as TSP, a DRL-based method is applied to optimize the sequence of items to be packed into the bin. Numerical results show that the method proposed in this paper achieve about 5% improvement than heuristic method.