Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping

Guangyi Liu, Suzan Iloglu, Michael Caldara, Joseph W Durham, Michael M. Zavlanos
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38722-38743, 2025.

Abstract

In Amazon robotic warehouses, the destination-to-chute mapping problem is crucial for efficient package sorting. Often, however, this problem is complicated by uncertain and dynamic package induction rates, which can lead to increased package recirculation. To tackle this challenge, we introduce a Distributionally Robust Multi-Agent Reinforcement Learning (DRMARL) framework that learns a destination-to-chute mapping policy that is resilient to adversarial variations in induction rates. Specifically, DRMARL relies on group distributionally robust optimization (DRO) to learn a policy that performs well not only on average but also on each individual subpopulation of induction rates within the group that capture, for example, different seasonality or operation modes of the system. This approach is then combined with a novel contextual bandit-based estimator of the worst-case induction distribution for each state-action pair, significantly reducing the cost of exploration and thereby increasing the learning efficiency and scalability of our framework. Extensive simulations demonstrate that DRMARL achieves robust chute mapping in the presence of varying induction distributions, reducing package recirculation by an average of 80% in the simulation scenario.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-liu25ad, title = {Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping}, author = {Liu, Guangyi and Iloglu, Suzan and Caldara, Michael and Durham, Joseph W and Zavlanos, Michael M.}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {38722--38743}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/liu25ad/liu25ad.pdf}, url = {https://proceedings.mlr.press/v267/liu25ad.html}, abstract = {In Amazon robotic warehouses, the destination-to-chute mapping problem is crucial for efficient package sorting. Often, however, this problem is complicated by uncertain and dynamic package induction rates, which can lead to increased package recirculation. To tackle this challenge, we introduce a Distributionally Robust Multi-Agent Reinforcement Learning (DRMARL) framework that learns a destination-to-chute mapping policy that is resilient to adversarial variations in induction rates. Specifically, DRMARL relies on group distributionally robust optimization (DRO) to learn a policy that performs well not only on average but also on each individual subpopulation of induction rates within the group that capture, for example, different seasonality or operation modes of the system. This approach is then combined with a novel contextual bandit-based estimator of the worst-case induction distribution for each state-action pair, significantly reducing the cost of exploration and thereby increasing the learning efficiency and scalability of our framework. Extensive simulations demonstrate that DRMARL achieves robust chute mapping in the presence of varying induction distributions, reducing package recirculation by an average of 80% in the simulation scenario.} }
Endnote
%0 Conference Paper %T Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping %A Guangyi Liu %A Suzan Iloglu %A Michael Caldara %A Joseph W Durham %A Michael M. Zavlanos %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-liu25ad %I PMLR %P 38722--38743 %U https://proceedings.mlr.press/v267/liu25ad.html %V 267 %X In Amazon robotic warehouses, the destination-to-chute mapping problem is crucial for efficient package sorting. Often, however, this problem is complicated by uncertain and dynamic package induction rates, which can lead to increased package recirculation. To tackle this challenge, we introduce a Distributionally Robust Multi-Agent Reinforcement Learning (DRMARL) framework that learns a destination-to-chute mapping policy that is resilient to adversarial variations in induction rates. Specifically, DRMARL relies on group distributionally robust optimization (DRO) to learn a policy that performs well not only on average but also on each individual subpopulation of induction rates within the group that capture, for example, different seasonality or operation modes of the system. This approach is then combined with a novel contextual bandit-based estimator of the worst-case induction distribution for each state-action pair, significantly reducing the cost of exploration and thereby increasing the learning efficiency and scalability of our framework. Extensive simulations demonstrate that DRMARL achieves robust chute mapping in the presence of varying induction distributions, reducing package recirculation by an average of 80% in the simulation scenario.
APA
Liu, G., Iloglu, S., Caldara, M., Durham, J.W. & Zavlanos, M.M.. (2025). Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:38722-38743 Available from https://proceedings.mlr.press/v267/liu25ad.html.

Related Material