CFP last date
20 November 2026
Call for Paper
December Edition
IJCA solicits high quality original research papers for the upcoming December edition of the journal. The last date of research paper submission is 20 November 2026

Submit your paper
Know more
The week's pick
Responsive image
A Machine Learning-based Decision Framework for Demand Forecasting and Price Optimization in Competitive E-Commerce Environments

Aera K. Leboulluec Janhavi Datye
Random Articles
Reseach Article

Review of Decentralized Reinforcement Learning for Multi-Agent Robotic Task Scheduling

by Timileyin Okoya, Waliu Apena, Folasade Dahunsi, Olufunso Alowolodu
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 187 - Number 149
Year of Publication: 2026
Authors: Timileyin Okoya, Waliu Apena, Folasade Dahunsi, Olufunso Alowolodu
10.5120/ijca28de3ec5ef45

Timileyin Okoya, Waliu Apena, Folasade Dahunsi, Olufunso Alowolodu . Review of Decentralized Reinforcement Learning for Multi-Agent Robotic Task Scheduling. International Journal of Computer Applications. 187, 149 ( Oct 2026), 18-25. DOI=10.5120/ijca28de3ec5ef45

@article{ 10.5120/ijca28de3ec5ef45,
author = { Timileyin Okoya, Waliu Apena, Folasade Dahunsi, Olufunso Alowolodu },
title = { Review of Decentralized Reinforcement Learning for Multi-Agent Robotic Task Scheduling },
journal = { International Journal of Computer Applications },
issue_date = { Oct 2026 },
volume = { 187 },
number = { 149 },
month = { Oct },
year = { 2026 },
issn = { 0975-8887 },
pages = { 18-25 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume187/number149/review-of-decentralized-reinforcement-learning-for-multi-agent-robotic-task-scheduling/ },
doi = { 10.5120/ijca28de3ec5ef45 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2026-10-24T03:08:53.861677+05:30
%A Timileyin Okoya
%A Waliu Apena
%A Folasade Dahunsi
%A Olufunso Alowolodu
%T Review of Decentralized Reinforcement Learning for Multi-Agent Robotic Task Scheduling
%J International Journal of Computer Applications
%@ 0975-8887
%V 187
%N 149
%P 18-25
%D 2026
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Multi-robot task scheduling is fundamental to managing multi-agent robotic systems (MARS) in unpredictable environments such as logistics, disaster management and autonomous exploration. Centralized task allocation scales poorly and adapts slowly to change, and reinforcement learning (RL) offers an alternative in which robots learn scheduling strategies through interaction. This review analyses 75 studies on multi-agent task allocation with RL, with particular attention to PettingZoo’s Pistonball environment as a multi-agent RL (MARL) benchmark. It combines a bibliometric profile of the corpus, a side-by-side comparison of representative studies, a qualitative comparison of learning paradigms and a graded appraisal of the evidence behind five recurring claims. Fully decentralized learning remains difficult because concurrent policy updates produce non-stationarity, whereas centralized training with decentralized execution (CTDE) has proved more practicable; hardware-validated schedulers are the weakest-supported area. The review identifies the need for systematic comparison of CTDE-based algorithms for vision-based multi-robot task scheduling under identical conditions in the Pistonball environment.

References
  1. Tejada, J. C., Toro-Ossaba, A., López-Gonzalez, A., et al. 2025. Multi-robot systems and soft robotics: Challenges and opportunities in a review. Sensors, 25(5), 1353.
  2. Parker, L. E. 2008. Multiple mobile robot systems. In B. Siciliano & O. Khatib (Eds.), Springer Handbook of Robotics (pp. 921–941). Springer.
  3. Owojori, A. O., Akingbade, K. F., Apena, W. O., and Ogunti, E. O. 2021. Stability control modelling under dynamic motion scenario of a differential drive robot. Journal of Engineering Studies and Research, 27(3), 64–73.
  4. Chakraa, H., Guérin, F., Leclercq, E., and Lefebvre, D. 2023. Optimization techniques for multi-robot task allocation problems: Review on the state-of-the-art. Robotics and Autonomous Systems, 168, 104492.
  5. Wang, Z., and Gombolay, M. 2020. Learning scheduling policies for multi-robot coordination with graph attention networks. IEEE Robotics and Automation Letters, 5(3), 4509–4516.
  6. Li, Z., Shi, N., Zhao, L., and Zhang, M. 2024. Deep reinforcement learning path planning and task allocation for multi-robot collaboration. Alexandria Engineering Journal, 109, 408–423.
  7. Dai, Y., Kim, D., and Lee, K. 2024. Development of fleet management system for task assignment to multiple robots using deep reinforcement learning. Processes, 12(12), 2921.
  8. Shibata, K., Jimbo, T., Odashima, T., et al. 2023. Learning locally, communicating globally: Reinforcement learning of multi-robot task allocation for cooperative transport. IFAC-PapersOnLine, 56(2), 11436–11443.
  9. Buşoniu, L., Babuška, R., and Schutter, B. 2010. Multi-agent reinforcement learning: An overview. In Innovations in Multi-Agent Systems and Applications (pp. 183–221). Springer.
  10. Low, D., and Zhou, Y. 2025. Cooperative multi-agent reinforcement learning for robotic systems: A review. Multiagent and Grid Systems, 21, 96–123.
  11. Liang, J., Miao, H., Li, K., et al. 2025. A review of multi-agent reinforcement learning algorithms. Electronics, 14(4), 820.
  12. Canese, L., Cardarilli, G., Di Nunzio, L., et al. 2021. Multi-agent reinforcement learning: A review of challenges and applications. Applied Sciences, 11, 4948.
  13. Jiang, J., Su, K., and Lu, Z. 2024. Fully decentralized cooperative multi-agent reinforcement learning: A survey. ArXiv, abs/2401.04934.
  14. Sharma, P., Fernandez, R., Zaroukian, E. G., et al. 2021. Survey of recent multi-agent reinforcement learning algorithms utilizing centralized training. In Proceedings of SPIE, 117462K–117462K-12.
  15. Hu, J. 2025. A survey on reinforcement learning-based multi-agent path planning. ITM Web of Conferences, 78, 01015.
  16. Alirezazadeh, S., and Alexandre, L. A. 2024. Survey on task allocation and scheduling in robotic network systems. IEEE Internet of Things Journal, 12(2), 1484–1508.
  17. Evans, O., and Patel, M. 2025. Robotic swarm intelligence: Coordination and collaboration in multi-robot systems. International Journal on Mechanical Engineering and Robotics, 13(1), 17–22.
  18. Xu, W., Gu, J., Zhang, W., et al. 2025. A survey on multi-agent reinforcement learning approaches for solving flexible shop scheduling problems. Frontiers in Industrial Engineering, 3, 1611512.
  19. Afrin, M., Jin, J., Rahman, A., et al. 2021. Resource allocation and service provisioning in multi-agent cloud robotics: A comprehensive survey. IEEE Communications Surveys & Tutorials, 23, 842–870.
  20. Alqefari, S., and Menai, M. 2025. Multi-UAV task assignment in dynamic environments: Current trends and future directions. Drones, 9(1), 75.
  21. Athira, K. A., Divya Udayan, J., and Subramaniam, U. 2024. A systematic literature review on multi-robot task allocation. ACM Computing Surveys, 57(3), 1–28.
  22. Tarafdar, R. 2025. Reinforcement learning in embodied and multi-agent environments: Progress, challenges, and prospects. International Journal of Innovative Science and Research Technology (IJISRT), IJISRT25MAR1376, 3183–3187.
  23. Li, L., Yang, B., Chen, C., et al. 2025. Intelligent multi-robot exploration in non-exposed spaces: Methods and challenges. Artificial Intelligence Review, 58.
  24. Gergely, M. I. 2024. Multi-agent deep reinforcement learning for collaborative task scheduling. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence (ICAART) (Vol. 3, pp. 1076–1083).
  25. Song, P., Chen, H., Cui, K., et al. 2025. Meta-learning for dynamic multi-robot task scheduling. Computers & Operations Research, 182.
  26. Wu, S., Fu, L., Chang, R., et al. 2025. Warehouse robot task scheduling using reinforcement learning for maximizing operational efficiency [Preprint]. TechRxiv.
  27. Schulman, J., Wolski, F., Dhariwal, P., et al. 2017. Proximal policy optimization algorithms. ArXiv, abs/1707.06347.
  28. Terry, J. K., Black, B., Grammel, N., et al. 2021. PettingZoo: Gym for multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 34, 15032–15043.
  29. Zhang, Y., and Parker, L. E. 2013. Multi-robot task scheduling. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (pp. 2992–2998). IEEE.
  30. Lerman, K., Jones, C., Galstyan, A., and Matarić, M. J. 2006. Analysis of dynamic task allocation in multi-robot systems. The International Journal of Robotics Research, 25(3), 225–241.
  31. Bischoff, E., Meyer, F., Inga, J., and Hohmann, S. 2020. Multi-robot task allocation and scheduling considering cooperative tasks and precedence constraints. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 3949–3956). IEEE.
  32. Suslova, E., and Fazli, P. 2020. Multi-robot task allocation considering time windows and sequencing constraints. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 6909–6916). IEEE.
  33. Zhang, C., and Shah, J. A. 2016. Multi-agent placement, task assignment, and scheduling in the cloud. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) (pp. 3308–3314). AAAI Press.
  34. Wang, H., and Chen, W. 2021. Task scheduling for transport and pick robots in logistics. Autonomous Intelligent Systems, 1(1), 17.
  35. Shakeri, M., Yazdani, M., and Faal, H. 2025. A genetic algorithm for multi-robot task allocation and scheduling in flexible job shop environments. International Journal of Production Research, 63(8), 2673–2693.
  36. Wang, H., Chen, W., and Wang, J. 2020. Coupled task scheduling for heterogeneous multi-robot systems. Robotics and Autonomous Systems, 131, 103560.
  37. Oroojlooyjadid, A., and Hajinezhad, D. 2019. A review of cooperative multi-agent deep reinforcement learning. Applied Intelligence, 53, 13677–13722.
  38. Li, P., Li, S., and Wang, J. 2026. The cooperation and competition mechanisms in multi-agent reinforcement learning. ITM Web of Conferences, 84, 04004.
  39. Papoudakis, G., Christianos, F., Rahman, A., and Albrecht, S. V. 2019. Dealing with non-stationarity in multi-agent deep reinforcement learning. ArXiv, abs/1906.04737.
  40. Gabler, V., and Wollherr, D. 2024. Decentralized multi-agent reinforcement learning based on best-response policies. Frontiers in Robotics and AI, 11.
  41. Bernstein, D., Givan, R., Immerman, N., and Zilberstein, S. 2002. The complexity of decentralized control of Markov decision processes. Mathematics of Operations Research, 27(4), 819–840.
  42. LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.
  43. Hochreiter, S., and Schmidhuber, J. 1997. Long short-term memory. Neural Computation, 9(8), 1735–1780.
  44. Park, S., Zhong, Y. D., and Leonard, N. E. 2021. Multi-robot task allocation games in dynamically changing environments. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) (pp. 8678–8684). IEEE.
  45. Kalempa, V. C., Piardi, L., Limeira, M., and de Oliveira, A. S. 2023. Multi-robot task scheduling for consensus-based fault-resilient intelligent behavior in smart factories. Machines, 11(4), 431.
  46. Mokhtari, M., Sadati, S. M., Dorri-Nowkoohdan, M. M., and Shah-Hosseini, H. 2025. Energy-aware scheduling in robotic swarms: A meta-heuristic approach. Journal of Ambient Intelligence and Humanized Computing, 16(3), 1117–1131.
  47. Sharma, K., Hassan, M. M., Pandey, S., et al. 2023. Cloud based multi-robot task scheduling using PMW algorithm. IEEE Access, 11, 146003–146013.
  48. Kim, S., and Lee, H. 2023. Multi-robot task scheduling with ant colony optimization in Antarctic environments. Sensors, 23(2), 751.
  49. Choudhury, S., Gupta, J. K., Kochenderfer, M. J., et al. 2022. Dynamic multi-robot task allocation in uncertain conditions and under temporal constraints. Autonomous Robots, 46(1).
  50. Zhu, X., Xu, J., Ge, J., et al. 2023. Multi-task multi-agent reinforcement learning for real-time scheduling of a dual-resource flexible job shop with robots. Processes, 11(1), 26.
  51. Zhu, C., Dastani, M., and Wang, S. 2022. A survey of multi-agent deep reinforcement learning with communication. Autonomous Agents and Multi-Agent Systems, 38, 1–48.
  52. Cao, X., Başar, T., Diggavi, S., et al. 2023. Communication-efficient distributed learning: An overview. IEEE Journal on Selected Areas in Communications, 41, 851–873.
  53. Cazenille, L., Toquebiau, M., Lobato-Dauzier, N., et al. 2025. Signalling and social learning in swarms of robots. Philosophical Transactions of the Royal Society A, 383, 20240148.
  54. Liu, D., Ren, F., Yan, J., et al. 2024. Scaling up multi-agent reinforcement learning: An extensive survey on scalability issues. IEEE Access, 12, 94610–94631.
  55. Myakala, P. K., and Kamatala, S. 2023. Scalable decentralized multi-agent federated reinforcement learning: Challenges and advances. International Journal of Electrical, Electronics and Computers, 8(6).
  56. Oesterle, M., Grams, T., and Bartelt, C. 2024. DRAMA at the PettingZoo: Dynamically restricted action spaces for multi-agent reinforcement learning frameworks. In Proceedings of the 57th Hawaii International Conference on System Sciences (pp. 7810–7819).
  57. Lee, K. M., Subramanian, S. G., and Crowley, M. 2021. Investigation of independent reinforcement learning algorithms in multi-agent environments. Frontiers in Artificial Intelligence, 5, 805823.
  58. Arifi, H., and Zhi, G. 2025. Reinforcement learning based training for maze craze computer game. Journal of Computer Sciences and Informatics, 2(3), 191–202.
  59. Adhikari, N., and Gu, A. 2024. Efficient learning in Chinese checkers: Comparing parameter sharing in multi-agent reinforcement learning. ArXiv, abs/2405.18733.
  60. Kamthan, A. 2025. Learning to lead themselves: Agentic AI in MAS using MARL. ArXiv, abs/2510.00022.
  61. Papadopoulos, G., Kontogiannis, A., Papadopoulou, F., et al. 2025. An extended benchmarking of multi-agent reinforcement learning algorithms in complex fully cooperative tasks. ArXiv, abs/2502.04773, 1613–1622.
  62. Felten, F., Ucak, U., Azmani, H., et al. 2024. MOMAland: A set of benchmarks for multi-objective multi-agent reinforcement learning. ArXiv, abs/2407.16312.
  63. Dai, W., Rai, U., Chiun, J., et al. 2025. Task allocation and scheduling of heterogeneous multiple robots using reinforcement learning. IEEE Robotics and Automation Letters, 10(3), 2654–2661.
  64. Metelo, F., Racković, S., Ákos, P., and Soares, C. 2024. PeersimGym: An environment for solving the task offloading problem with reinforcement learning. ArXiv, abs/2403.17637.
  65. Kölle, M., Erpelding, Y., Ritz, F., et al. 2024. Aquarium: A comprehensive framework for exploring predator-prey dynamics through multi-agent reinforcement learning algorithms. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence (ICAART) (Vol. 1, pp. 59–70).
  66. Kayal, A., and Ravimaran, S. 2026. Experimental evaluation of coordinated decision-making strategies based on multi-agent reinforcement learning. In Proceedings of the International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES) (pp. 1–9). IEEE.
  67. Zhang, W. 2025. Cooperative path planning of multiple robots: Advances, challenges, and future trends. Highlights in Science, Engineering and Technology, 147, 359–364.
  68. Zhao, W., Queralta, J. P., and Westerlund, T. 2020. Sim-to-real transfer in deep reinforcement learning for robotics: A survey. In Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 737–744). IEEE.
  69. Salvato, E., Fenu, G., Medvet, E., and Pellegrino, F. A. 2021. Crossing the reality gap: A survey on sim-to-real transferability of robot controllers in reinforcement learning. IEEE Access, 9, 153171–153187.
  70. Hua, M., Qi, X., Chen, D., et al. 2023. Multi-agent reinforcement learning for connected and automated vehicles control: Recent advancements and future prospects. IEEE Transactions on Automation Science and Engineering, 22, 16266–16286.
  71. Tang, C., Abbatematteo, B., Hu, J., et al. 2024. Deep reinforcement learning for robotics: A review of real-world success cases. ArXiv, abs/2408.03539.
  72. Feriani, A., and Hossain, E. 2020. Single and multi-agent deep reinforcement learning for AI-enabled wireless networks: A tutorial. IEEE Communications Surveys & Tutorials, 23, 1226–1252.
  73. Beltrán, E. T. M., Pérez, M. Q., Sánchez, P. M. S., et al. 2023. Decentralized federated learning: Fundamentals, state of the art, frameworks, trends, and challenges. IEEE Communications Surveys & Tutorials, 25(4), 2983–3013.
  74. Chung, S.-J., Paranjape, A., Dames, P., et al. 2018. A survey on aerial swarm robotics. IEEE Transactions on Robotics, 34(4), 837–855.
  75. Sun, L., Yang, Y., Duan, Q., et al. 2025. Coordination of multi-agents for various applications. ArXiv, abs/2502.14743.
Index Terms

Computer Science
Information Sciences

Keywords

Multi-agent reinforcement learning decentralized control task scheduling multi-robot systems centralized training decentralized execution PettingZoo Pistonball

Powered by PhDFocusTM