ABSTRACT
The AbstractSwarm Framework [1] was developed to study multi-agent simulation for optimizing logistics scenarios, with a special focus on (but not restricted to) hospital logistics. The basics of a solution to the accompanying competition [2] and the included benchmark problems is to be presented in this paper. To achieve this, Q-Learning [5, 7, 8] is used to determine scores for possible actions an agent can take depending on the state of the AbstractSwarm Graph representing the environment. Every action receives multiple such scores which are in turn aggregated, hence the name "QPlus".
- Daan Apeldoorn. [n. d.]. AbstractSwarm - A Generic Graphical Modeling Language for Multi-Agent Systems. In Multiagent System Technologies. Vol. 8076. Springer Berlin Heidelberg, 180--192. Google ScholarCross Ref
- Daan Apeldoorn, Alexander Dockhorn, Lars Hadidi, and Torsten Panholzer. [n. d.]. AbstractSwarm Competition. https://abstractswarm.gitlab.io/abstractswarm_competition/ Accessed 2022-04-09.Google Scholar
- T. Kohonen. [n. d.]. The self-organizing map. 78, 9 ([n. d.]), 1464--1480. Google ScholarCross Ref
- Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis. [n. d.]. Human-level control through deep reinforcement learning. 518, 7540 ([n. d.]), 529--533. Google ScholarCross Ref
- Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement learning: An introduction. MIT press.Google Scholar
- Gerald Tesauro. [n. d.]. Extending Q-learning to general adaptive multi-agent systems. 16 ([n. d.]).Google Scholar
- C.J. C.H. Watkins. [n. d.]. Learning from delayed rewards. https://www.academia.edu/3294050/Learning_from_delayed_rewardsGoogle Scholar
- Christopher J. C. H. Watkins and Peter Dayan. [n. d.]. Q-learning. 8, 3--4 ([n. d.]), 279--292. Google ScholarDigital Library
Index Terms
- AbstractSwarm multi-agent logistics competition entry: QPlus
Recommendations
Multi-agent framework for third party logistics in E-commerce
In an e-commerce environment, the third party logistics (3PL) takes charge of the logistics design, delivery, storage and transportation in a supply chain with its professional and complete value-added services. Beginning with an analysis of the ...
Effective service composition using multi-agent reinforcement learning
As online services may keep evolving, service composition should maintain certain adaptivity especially for a dynamic composition environment. Meanwhile, the large number of potential candidate services poses scalability concerns, which demand efficient ...
Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward
AAMAS '18: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent SystemsWe study the problem of cooperative multi-agent reinforcement learning with a single joint reward signal. This class of learning problems is difficult because of the often large combined action and observation spaces. In the fully centralized and ...
Comments