Curriculum Reinforcement Learning for Progressive Coordination in Complex Multi-Step Decision Tasks

Authors

  • Pierre Dupont Department of Computer Science, École Polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France Author
  • Marie Lefèvre Department of Computer Science, École Polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France Author
  • Antoine Martin Department of Computer Science, École Polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France Author

DOI:

https://doi.org/10.66525/ijictt75

Keywords:

Curriculum learning, Reinforcement learning, PPO, Multi-agent coordination, Task complexity

Abstract

 Training collaborative agents directly on complex tasks often leads to unstable learning and poor convergence. This study proposes a curriculum reinforcement learning strategy in which task difficulty is gradually increased based on coordination complexity and dependency depth. A dynamic curriculum scheduler is designed using reward variance and policy entropy as progression signals, while PPO is used for policy optimization. The framework is evaluated on 12,000 tasks with increasing levels of complexity, from simple coordination to multi-stage planning with constraints. Compared with direct training, the curriculum-based approach improves final task success rate by 18.7% and accelerates convergence by 26.9%. In addition, failure cases related to coordination breakdown are reduced by 31.2%. The results indicate that structured training progression significantly enhances learning stability and performance in collaborative decision environments. 

Downloads

Download data is not yet available.

References

Qiu, Y. (2024). Estimation of tail risk measures in finance: Approaches to extreme value mixture modeling. arXiv preprint arXiv:2407.05933.

Gronauer, S., & Diepold, K. (2022). Multi-agent deep reinforcement learning: a survey. Artificial Intelligence Review, 55(2), 895-943.

Xu, D., Liu, H., Qiu, D., & Ma, Q. (2026). Structured Modeling and Representation Methods for Post-Retrieval Inference Processes in Large Video Language Models.

Shaukat, S. U., Khan, S., & Parkinson, S. (2025). A Review on Multi-step Attack Detection. IEEE Access.

Liu, S., Liu, X., & Feng, H. (2025, November). Research on AI-Driven Visual Design and Immersive Interactive Experiences Based on Multimodal Cognition and User. In Proceedings of the 2025 International Conference on Digital Society and Intelligent Computing (pp. 734-740).

Abadi, A. S., & Soh, L. K. (2025). Challenges in Credit Assignment for Multi-Agent Reinforcement Learning in Open Agent Systems. arXiv preprint arXiv:2510.27659.

Gao, G., Gao, R., Gao, R., & Zhou, H. (2026). Engineering Analysis and Quantitative Research on the Platform-Based Evolution of Enterprise Communication Systems.

Del Rio, A., Jimenez, D., & Serrano, J. (2024). Comparative analysis of A3C and PPO algorithms in reinforcement learning: A survey on general environments. IEEe Access, 12, 146795-146806.

Xu, D., Chen, H., & Gui, H. (2026). Unified Online Estimation Method for SOC, SOH, and Power Capacity Considering Safety Boundary Consistency in Battery Management Systems.

Gupta, K., Mukherjee, D., & Najjaran, H. (2022). Extending the capabilities of reinforcement learning through curriculum: A review of methods and applications. SN Computer Science, 3(1), 28.

Wang, Y., Chen, J., Wang, Y., & Yin, X. (2026). Application of Obtainable Biological Agent Characteristics in Efficacy Stratification of Oral Anti-Obesity Drugs.

Lagomarsino, M., Merlo, E., Pupa, A., Birr, T., Krebs, F., Secchi, C., ... & Ajoudani, A. (2025). Intuitive Programming, Adaptive Task Planning, and Dynamic Role Allocation in Human–Robot Collaboration. Annual Review of Control, Robotics, and Autonomous Systems, 9.

Zhang, Y., Gu, W., & Wang, J. (2025). Research on First Article Inspection (FAI)-Driven Quality Assurance Methods for Wind Turbine Installation and Operation & Maintenance and Their Effect on Reliability Improvement. Available at SSRN 6094206.

Thang, T. B., & Binh, H. T. T. (2024). Multitask Augmented Random Search in deep reinforcement learning. Applied Soft Computing, 160, 111605.

Liu, H., Xu, D., Ma, Q., Xu, S., & Qiu, D. (2026). Memory Poisoning Propagation and Repair Mechanism in Multi-Agent Collaborative Environments.

Massaoudi, M. S., Abu-Rub, H., & Ghrayeb, A. (2023). Navigating the landscape of deep reinforcement learning for power system stability control: A review. IEEE access, 11, 134298-134317.

Zhang, Y., & Wang, J. (2026). Design and Implementation of a Computer-Aided Full Lifecycle Quality Management System for Wind Farms in Upgrades, Renovations, and Subcontractor Supervision.

Thaariq, Z. Z. A., & Karakuş, M. (2025). Designing a Methodological Framework for Assessing Teacher Readiness in Adaptive Curriculum Implementation within Indonesian Context. Journal of Curriculum and Learning Technologies (JCLT-Krisno), 1(2), 54-69.

Jiao, Y., Wang, A., Zhao, B., & Shi, T. (2026). Quantitative Study on the Construction and Application Effectiveness of Graffiti Wall Painting Teaching Models in Public Space Contexts.

Damayanti, I., Baqy, I., & Rokhmat, J. (2025). A Systematic Review of Research Trends in Cooperative Learning Models in Science Learning. Contextual Natural Science Education Journal, 3(2), 1-14.

Wang, Y., Yin, X., Chen, J., & Wang, Y. (2026). Evidence-Based Study on Low-Burden Digital Phenotyping for Precision Screening of Oral Anti-Obesity Drug Efficacy.

Nungu, L., Mukama, E., & Nsabayezu, E. (2023). Online collaborative learning and cognitive presence in mathematics and science education. Case study of university of Rwanda, college of education. Education and Information Technologies, 28(9), 10865-10884.

Xu, D., Gui, H., & Chen, H. (2026). Research on Layered Control and Fault Recovery Mechanisms for Fast Charging Safety Diagnosis of High Voltage Battery Systems Under Charging Network Interoperability Conditions.

Kaven, L., Huke, P., Göppert, A., & Schmitt, R. H. (2024). Multi agent reinforcement learning for online layout planning and scheduling in flexible assembly systems. Journal of Intelligent Manufacturing, 35(8), 3917-3936.

Ahmad, N. R. (2025). Exploring the role of digital technologies in enhancing supply chain efficiency: A case study of e-commerce companies. Indus Journal of Social Sciences, 3(1), 226–237. https://doi.org/10.59075/ijss.v3i1.618

Downloads

Published

2026-04-01