All publications from Manu Kumar Gupta (PI) are available in Google Scholar. All publications of the lab are listed below.

Peer reviewed articles

  1. Bihareelal Meghwal, Manu K. Gupta and Shiv Kumar Gupta. "Learning to Solve Many-to-Many Pickup and Delivery Problems With Multi-Head Heterogeneous Attention" IEEE Transactions on Intelligent Transportation Systems (TITS), 2026. [PDF] [Code]
    Recently, deep reinforcement learning has gained attention for solving routing problems due to its ability to learn complex patterns and optimize sequential decision-making. Despite their success in various routing problems, the applicability of learning-based methods on pickup and delivery problems (PDPs) is limited and only addresses one-to-one PDPs and their variants. However, the many-to-many PDP addressed in this paper is a practical variant of the routing problems and finds several applications in logistics and supply chains. We propose a novel reinforcement learning framework empowered by a multi-head heterogeneous attention mechanism (MHHA) and a decoder capable of exploring a diverse set of solutions, namely HAP, to generate efficient solutions for many-to-many PDP. The proposed framework incorporates an encoder-decoder structure designed explicitly for many-to-many PDP. In particular, the encoder consists of the MHHA mechanism to capture the many-to-many relationships and effectively model the flow constraints. Moreover, it is integrated with the multi-solution generator, polynet and masking scheme to generate high-quality diverse solutions. Additionally, we improve the solution quality of HAP using a warm starting variable neighbourhood search. As extensive experimental results demonstrate, the proposed method outperforms state-of-the-art metaheuristic and learning-based approaches. Additionally, in bi-objective (time and gap) comparison, the HAP lies on the Pareto efficient frontier, proving its effectiveness. Moreover, the HAP effectively generalizes to diverse problem sizes, unseen data distributions, benchmark datasets, and also solves one-to-one PDP more effectively than baseline methods, showing its adaptability and robustness. Finally, we conduct ablation studies to justify the proposed design

  2. Anirban Mitra, Manu K. Gupta, and N. Hemachandra. "Strategic Interaction Between Queueing System and Impatient User-Base." International Conference on Network Games, Artificial Intelligence, Control and Optimization (NETGCOOP). Cham: Springer Nature Switzerland, 2025. [PDF]

  3. Aditi Jha, S. Kumar and Manu K. Gupta, "Deep Reinforcement Learning algorithm for Capacitated Pollution Routing Problem," 5th International Conference on Sustainable Energy and Future Electric Transportation (SEFET), Jaipur, India, 2025, pp. 1-6. [PDF]

  4. Gopal Saha and Manu K. Gupta. "Fair cost savings allocation in two-stage fixed-cost transportation problem." Information Systems and Operational Research (INFOR) : 1-39, 2025. [PDF] [Code]
    This paper navigates the economic efficiency in a two-stage fixed-cost transportation problem (TS-FCTP), employing cooperative game theory (CGT) for fair allocation in a shared transportation network. Collaboration among Logistics Service Providers (LSPs) in a multi-echelon supply chain network, such as in TS-FCTP, emerges as a pivotal strategy to reduce costs and enhance network efficiency. The allocation of these cost savings among LSPs becomes a crucial question, prompting the introduction of a transportation game (TG) with LSPs as players. Diverse CGT solution concepts are explored to distribute cost savings among participating LSPs. We consider both synthetic and real datasets. For these datasets, we notice that the transportation game is monotonic and superadditive, and the core is non-empty. These properties indicate the willingness of players to form a coalition. Additionally, we determine the most stable cost savings allocation using the core center concept. The optimal coalition formation sequence has been identified using the Shapley monotonic path. Our findings illustrate that LSPs bear lower costs when cooperating with other LSPs. In this TG, individual players’ utility is computed by solving a TS-FCTP. This can be computationally intensive, even for medium-sized problem instances. We propose two valid inequalities (VIs) that significantly reduce the computation time.

  5. Manas Shil, G. N. Pillai and Manu K. Gupta, “Multi-Agent Deep Reinforcement Learning based Secondary Voltage Control of Inverter-Based AC Microgrids”, Annual Conference of the IEEE Industrial Electronics Society (IECON), 2024. [PDF]

  6. Manas Shil, G. N. Pillai and Manu K. Gupta, “Improved Soft Actor-Critic: Reducing Bias and Estimation Error for Fast Learning”, IEEE International Students' Conference on Electrical, Electronics and Computer Sciences (SCEECS), 2023. [PDF]

  7. G. Saha and Manu K. Gupta, "Fair Cost-Savings Allocation in Transportation Game," IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Singapore, Singapore, 2023 [PDF]

  8. A. Mitra, Manu K. Gupta and N. Hemachandra, “Cooperative Game Theoretic Analysis of Shared Services” 15th International Conference on Performance Evaluation Methodologies and Tools (ValueTools), Ghent, Belgium (Virtual), 2022 . [PDF]


Other conferences/talks/posters

  1. A. Mitra, Manu K. Gupta and N. Hemachandra, “Strategic interaction between service providers and the user-set in (abandonment) queues”, International Conference on Operations Research and Game Theoretic Approach in Decision Making, ISI Delhi, 2024.
  2. Manu K. Gupta, “A unifying computation scheme of Whittle's indices for Markovian bandits ”, Workshop on restless bandits, index policies and applications in reinforcement learning, Grenoble, France, 2023. Workshop Link
  3. Muskan Goel and Manu K. Gupta, “Reinforcement Learning for Intelligent and Automated Operation Planning”, Poster presentation at International Conference On Shaping the Future of Management Education for Sustainable Emerging Economies (SFME), 2022. PDF
  4. Gopal Saha and Manu K. Gupta, “Epidemic Models and Decision Support for Vaccine Distribution and Essential Medical Supplies”, Poster presentation at International Conference On Shaping the Future of Management Education for Sustainable Emerging Economies (SFME), 2022. PDF
  5. Anirban Mitra, Manu K. Gupta and N. Hemachandra, “Cooperative Game Theoretic Models to Analyze Multi-class Queueing Systems”, The International Conference “Game Theory and Applications” (GTA), 2022. Slides