Preprint · 2026 · Open access

Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation

Rifny Rachman, Bahrul Ilmi Nasution, Josh Tingey, Richard Allmendinger, Pradyumn Kumar Shukla, Wei Pan

arXiv (Cornell University) · Published 20 June 2026 · DOI 10.48550/arxiv.2606.22146

Open PDFView at the publisherCite this paper

In brief

“Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation” is a 2026 preprint by Rifny Rachman and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at arXiv (Cornell University).

Citations
0
References
57
Authors
6

Abstract

Meta-reinforcement learning is a promising approach to multi-objective optimisation because it enables rapid policy adaptation across changing environments and preference settings. However, conventional few-shot methods usually fine-tune from a single shared meta-policy, which can reduce solution diversity and limit exploration of the Pareto front, especially in high-dimensional combinatorial problems such as supply chain optimisation. We propose a population-based Meta-reinforcement learning framework that combines decomposition with evolutionary search in scalarisation weight space. The framework maintains a population of weight vectors, each associated with a distinct meta-policy trained through gradient-based meta-learning, and iteratively refines this population through elitist selection, crossover, and mutation guided by hypervolume and entropy contributions. We evaluate the method in a multi-objective supply chain setting with conflicting economic, environmental, and social goals, and further test its generality on standard reinforcement learning problems. The results show that the proposed approach yields more diverse, better distributed Pareto front approximations, improves cross-task adaptation, increases hypervolume by up to 32\% over Meta-multi-objective reinforcement learning in the complex case, and attains the lowest average Hausdorff distance among all compared methods.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Rachman, R., Nasution, B. I., Tingey, J., Allmendinger, R., Shukla, P. K., & Pan, W. (2026). Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.22146

MLA 9

Rachman, Rifny, et al. “Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2606.22146.

Chicago

Rachman, Rifny, Bahrul Ilmi Nasution, Josh Tingey, Richard Allmendinger, Pradyumn Kumar Shukla, and Wei Pan. 2026. “Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.22146.

Harvard

Rachman, R. et al. (2026) ‘Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation’, arXiv (Cornell University). doi:10.48550/arxiv.2606.22146.

IEEE

R. Rachman, B. I. Nasution, J. Tingey, R. Allmendinger, P. K. Shukla, and W. Pan, “Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2606.22146.

BibTeX

@misc{rachman2026meta,
  title     = {{Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation}},
  author    = {Rachman, Rifny and Nasution, Bahrul Ilmi and Tingey, Josh and Allmendinger, Richard and Shukla, Pradyumn Kumar and Pan, Wei},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2606.22146},
  url       = {https://doi.org/10.48550/arxiv.2606.22146}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computational Theory and Mathematics › Advanced Multi-Objective Optimization Algorithms

  • meta-reinforcement learning
  • multi-objective optimization
  • combinatorial optimization
  • supply chain optimization
  • evolutionary search
  • decomposition
  • hypervolume
  • entropy (information theory)

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Rachman, R., Nasution, B. I., Tingey, J., Allmendinger, R., Shukla, P. K., & Pan, W. (2026). Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.22146

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Rifny Rachman, Bahrul Ilmi Nasution, Josh Tingey, Richard Allmendinger, Pradyumn Kumar Shukla, Wei Pan.

What is the DOI of this paper?

10.48550/arxiv.2606.22146, permanently at https://doi.org/10.48550/arxiv.2606.22146. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.