Deep reinforcement learning with coalition action selection for online combinatorial resource allocation with arbitrary action space
Deep reinforcement learning with coalition action selection for online combinatorial resource allocation with arbitrary action space
Current DRL algorithms typically assume a fixed number of possible actions and sequentially select one action at a time, which makes them inefficient for resource allocation problems with arbitrarily large action spaces. Sequential action selection requires updating the state for every action selected, which increases the depth of the decision, the state space, the uncertainty, and the number of executions. This affects the convergence of the algorithm and slows the execution speed. Additionally, current DRL algorithms are not efficient for online resource allocation problems with an arbitrary number of task arrivals per time step because they assume a fixed number of actions. To address these challenges, we propose a novel coalition action selection approach that enables the DRL algorithm to simultaneously select a coalition of an arbitrary number of actions, from a set with an arbitrary number of possible actions. By making simultaneous decisions at each time step, coalition action selection avoids the need to update the state multiple times. We evaluate the performance and complexity of coalition action selection and sequential action selection approaches using an online combinatorial resource allocation problem. The results demonstrate that the coalition action selection approach retains close performance to the offline optimal for various online traffic demand arrival rates of the online combinatorial resource allocation problem, while the performance of the sequential action selection approach decreases as the size of the problem increases. The experiments also demonstrate that coalition action selection has much lower computational complexity than sequential action selection.
Gebrekidan, Tesfay Zemuy
289d7a6a-f783-42c4-9a77-e69e0d96d66e
Stein, Sebastian
cb2325e7-5e63-475e-8a69-9db2dfbdb00b
Norman, Timothy J.
663e522f-807c-4569-9201-dc141c8eb50d
6 May 2024
Gebrekidan, Tesfay Zemuy
289d7a6a-f783-42c4-9a77-e69e0d96d66e
Stein, Sebastian
cb2325e7-5e63-475e-8a69-9db2dfbdb00b
Norman, Timothy J.
663e522f-807c-4569-9201-dc141c8eb50d
Gebrekidan, Tesfay Zemuy, Stein, Sebastian and Norman, Timothy J.
(2024)
Deep reinforcement learning with coalition action selection for online combinatorial resource allocation with arbitrary action space.
The 23rd International Conference on Autonomous Agents and Multi-Agent Systems, Cordis Hotel, Auckland, New Zealand.
06 - 10 May 2024.
9 pp
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Current DRL algorithms typically assume a fixed number of possible actions and sequentially select one action at a time, which makes them inefficient for resource allocation problems with arbitrarily large action spaces. Sequential action selection requires updating the state for every action selected, which increases the depth of the decision, the state space, the uncertainty, and the number of executions. This affects the convergence of the algorithm and slows the execution speed. Additionally, current DRL algorithms are not efficient for online resource allocation problems with an arbitrary number of task arrivals per time step because they assume a fixed number of actions. To address these challenges, we propose a novel coalition action selection approach that enables the DRL algorithm to simultaneously select a coalition of an arbitrary number of actions, from a set with an arbitrary number of possible actions. By making simultaneous decisions at each time step, coalition action selection avoids the need to update the state multiple times. We evaluate the performance and complexity of coalition action selection and sequential action selection approaches using an online combinatorial resource allocation problem. The results demonstrate that the coalition action selection approach retains close performance to the offline optimal for various online traffic demand arrival rates of the online combinatorial resource allocation problem, while the performance of the sequential action selection approach decreases as the size of the problem increases. The experiments also demonstrate that coalition action selection has much lower computational complexity than sequential action selection.
Text
Coalition Action Selection - AAMAS Full Paper
More information
Accepted/In Press date: 21 December 2023
Published date: 6 May 2024
Venue - Dates:
The 23rd International Conference on Autonomous Agents and Multi-Agent Systems, Cordis Hotel, Auckland, New Zealand, 2024-05-06 - 2024-05-10
Identifiers
Local EPrints ID: 487159
URI: http://eprints.soton.ac.uk/id/eprint/487159
PURE UUID: 2148b115-c48c-42c7-9adc-88fbd2078239
Catalogue record
Date deposited: 14 Feb 2024 17:43
Last modified: 18 Mar 2024 03:34
Export record
Contributors
Author:
Tesfay Zemuy Gebrekidan
Author:
Sebastian Stein
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