Route Optimization via Environment-Aware Deep Network and Reinforcement Learning

  title={Route Optimization via Environment-Aware Deep Network and Reinforcement Learning},
  author={Pengzhan Guo and Keli Xiao and Zeyang Ye and Wei Zhu},
  journal={ACM Trans. Intell. Syst. Technol.},
Vehicle mobility optimization in urban areas is a long-standing problem in smart city and spatial data analysis. Given the complex urban scenario and unpredictable social events, our work focuses on developing a mobile sequential recommendation system to maximize the profitability of vehicle service providers (e.g., taxi drivers). In particular, we treat the dynamic route optimization problem as a long-term sequential decision-making task. A reinforcement-learning framework is proposed to… 

Figures and Tables from this paper

Deep reinforcement learning for the dynamic and uncertain vehicle routing problem

This paper proposes the formulation of a novel deep reinforcement learning framework to solve a dynamic and uncertain vehicle routing problem (DU-VRP), whose objective is to meet the uncertain servicing needs of customers in a dynamic environment.

Hierarchical Multi-agent Model for Reinforced MedicalResource Allocation with Imperfect Information

A hierarchical reinforcement learning framework with several specially designed components is proposed, which design an recurrent neural network based framework to utilize the imperfect information obtained from the environment and a multi-agents voting method, which modifies the decision making process considering the randomness during model training and thus improves the performance.

Synthetic Behavior Sequence Generation using Generative Adversarial Networks

This paper introduces a new Generative Adversarial Network (GAN) algorithm, namely BehavGAN, that applies GAN to the problem of behavior sequence generation and proposes an effective reward function for GAN backpropagation by incorporating n-gram based similarity measures in the reinforcement mechanism.

Intelligent career planning via stochastic subsampling reinforcement learning

An intelligent sequential career planning system featuring a career path rating mechanism and a new RL method coined as the stochastic subsampling reinforcement learning (SSRL) framework is proposed, showing that the initial state can have a significant impact, positively or negatively, on one’s career.

Contrastive Learning with Bidirectional Transformers for Sequential Recommendation

This work proposes a novel framework named Contrastive learning with Bidirectional Transformers for sequential recommendation (CBiT), which demonstrates better performance and adaptability compared with the normal one-pair contrastive learning, and introduces a novel dynamic loss reweighting strategy to balance between the cloze task loss and the contrastive loss.

Deriving the Optimal Strategy for the Two Dice Pig Game via Reinforcement Learning

This paper derives the optimal strategy for playing the two-dice game Pig, both the standard version and its variant with doubles, coined “Double-Trouble”, using certain fundamental concepts of reinforcement learning, especially the Markov decision process and dynamic programming.



Optimize taxi driving strategies based on reinforcement learning

The results show that the novel method based on reinforcement learning to optimize taxi driving strategies for global profit maximization improves profits and efficiency for cabdrivers and increases the opportunities for passengers to find taxis as well.

Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Improving Revenues

A Reinforcement Learning (RL) based system to learn from real trajectory logs of drivers to advise them on the right locations to find customers which maximize their revenue and it is demonstrated that an RL based system can provide significant benefits to the drivers.

Optimizing Taxi Driver Profit Efficiency: A Spatial Network-Based Markov Decision Process Approach

A novel Spatial Network-based Markov Decision Process (SN-MDP) with a rolling horizon configuration to recommend better driving directions given a set of historical taxi records and the current status of a vacant taxi to maximize the profit in the near future is proposed.

HUNTS: A Trajectory Recommendation System for Effective and Efficient Hunting of Taxi Passengers

This paper proposes a dynamic scoring system to evaluate each road segment in different time periods by considering both picking-up rate and profit factors, and introduces a novel method, called trajectory sewing, based on a heuristic method and the Skyline technique, to produce an approximate optimal trajectory in real-time.

TaxiRec: Recommending Road Clusters to Taxi Drivers Using Ranking-Based Extreme Learning Machines

TaxiRec is proposed, a framework for evaluating and discovering the passenger-finding potentials of road clusters, which is incorporated into a recommender system for taxi drivers to seek passengers and can use with a training cluster selection algorithm to provide road cluster recommendations when taxi trajectory data is incomplete or unavailable.

T-drive: driving directions based on taxi trajectories

This paper mine smart driving directions from the historical GPS trajectories of a large number of taxis, and provides a user with the practically fastest route to a given destination at a given departure time.

Weighted Aggregating Stochastic Gradient Descent for Parallel Deep Learning

An enhanced version of the weighted aggregating stochastic gradient descent scheme, WASGD+, is shown to be a significant improvement over its prototype and firmly validated the superiority of the WASGD scheme in accelerating the training of deep architecture.

Multi-User Mobile Sequential Recommendation for Route Optimization

This work enhances the mobile sequential recommendation (MSR) model and address some critical issues in existing formulations by proposing three new forms of the MSR from a multi-user perspective, and develops a parallel framework based on the simulated annealing to numerically solve the MMSR problem series.

Anomalous Taxi Route Detection System Based on Cloud Services

This paper proposes a solution which is a cloud-based system and applies machine learning algorithms to detect anomaly taxi trajectory for the passenger and demonstrates the system architecture design in detail.