Collaborating in a competitive world: heterogeneous multi-agent decision making in symbiotic supply chain environments
Collaborating in a competitive world: heterogeneous multi-agent decision making in symbiotic supply chain environments
Supply networks require collaboration in a competitive environment. To achieve this, nodes in the network often form symbiotic relationships as they can be adversely effected by the closure of companies in the network, especially where products are niche. However, balancing support for other nodes in the network against profit is challenging. Agents are increasingly being explored to define optimal strategies in these complex networks. However, To date much of the literature focuses on homogeneous agents where a single policy controls all of the nodes. This isn't realistic for many supply chains as this level of information sharing would require an exceptionally close relationship. This paper therefore compares the behaviour of this type of agent to a heterogeneous structure, where the agents each have separate polices, to solve the product ordering and pricing problem in supply chains where the relationships are symbiotic. As profit sharing seems unlikely in all but the closest relationships, an approach to reward sharing is developed that doesn't require sharing profit. The homogeneous and heterogeneous agents exhibit different behaviours, with the homogeneous retailer retaining high inventories and witnessing high backlog backlog levels while the heterogeneous agents show a typical order strategy. This leads to the heterogeneous agents mitigating the bullwhip effect whereas the homogeneous agents do not. In the high demand environment, the agent architecture dominates performance with the Soft Actor-Critic (SAC) agents outperforming the Proximal Policy Optimisation (PPO) agents. Here, the factory controls the supply chain. In the low demand environment the homogeneous agents outperform the heterogeneous agents. Control of the supply chain shifts significantly, with the retailer outperforming the factory by a significant margin.
Backlog and stock-out, Decision support systems, Inventory optimisation, Multi-agent systems, Pricing
Wang, Wan
b6fa846f-968a-4697-903e-8d42f7d293aa
Wang, Haiyan
5516425b-5b92-492d-8a48-2813d9a37639
Sobey, Adam J.
e850606f-aa79-4c99-8682-2cfffda3cd28
14 August 2025
Wang, Wan
b6fa846f-968a-4697-903e-8d42f7d293aa
Wang, Haiyan
5516425b-5b92-492d-8a48-2813d9a37639
Sobey, Adam J.
e850606f-aa79-4c99-8682-2cfffda3cd28
Wang, Wan, Wang, Haiyan and Sobey, Adam J.
(2025)
Collaborating in a competitive world: heterogeneous multi-agent decision making in symbiotic supply chain environments.
Computers & Industrial Engineering, 209, [111455].
(doi:10.1016/j.cie.2025.111455).
Abstract
Supply networks require collaboration in a competitive environment. To achieve this, nodes in the network often form symbiotic relationships as they can be adversely effected by the closure of companies in the network, especially where products are niche. However, balancing support for other nodes in the network against profit is challenging. Agents are increasingly being explored to define optimal strategies in these complex networks. However, To date much of the literature focuses on homogeneous agents where a single policy controls all of the nodes. This isn't realistic for many supply chains as this level of information sharing would require an exceptionally close relationship. This paper therefore compares the behaviour of this type of agent to a heterogeneous structure, where the agents each have separate polices, to solve the product ordering and pricing problem in supply chains where the relationships are symbiotic. As profit sharing seems unlikely in all but the closest relationships, an approach to reward sharing is developed that doesn't require sharing profit. The homogeneous and heterogeneous agents exhibit different behaviours, with the homogeneous retailer retaining high inventories and witnessing high backlog backlog levels while the heterogeneous agents show a typical order strategy. This leads to the heterogeneous agents mitigating the bullwhip effect whereas the homogeneous agents do not. In the high demand environment, the agent architecture dominates performance with the Soft Actor-Critic (SAC) agents outperforming the Proximal Policy Optimisation (PPO) agents. Here, the factory controls the supply chain. In the low demand environment the homogeneous agents outperform the heterogeneous agents. Control of the supply chain shifts significantly, with the retailer outperforming the factory by a significant margin.
Restricted to Repository staff only until 11 August 2028.
Request a copy
More information
Accepted/In Press date: 4 August 2025
e-pub ahead of print date: 11 August 2025
Published date: 14 August 2025
Keywords:
Backlog and stock-out, Decision support systems, Inventory optimisation, Multi-agent systems, Pricing
Identifiers
Local EPrints ID: 504925
URI: http://eprints.soton.ac.uk/id/eprint/504925
ISSN: 0360-8352
PURE UUID: 6d86a0db-5499-466f-a523-a2189b5251bb
Catalogue record
Date deposited: 22 Sep 2025 16:50
Last modified: 27 Sep 2025 01:44
Export record
Altmetrics
Contributors
Author:
Wan Wang
Author:
Haiyan Wang
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics