Nguyen, Quang Dang and Prokopenko, Mikhail (2020) Structure-Preserving Imitation Learning With Delayed Reward: An Evaluation Within the RoboCup Soccer 2D Simulation Environment. Frontiers in Robotics and AI, 7. ISSN 2296-9144
pubmed-zip/versions/2/package-entries/frobt-07-00123-r1/frobt-07-00123.pdf - Published Version
Download (2MB)
Abstract
We describe and evaluate a neural network-based architecture aimed to imitate and improve the performance of a fully autonomous soccer team in RoboCup Soccer 2D Simulation environment. The approach utilizes deep Q-network architecture for action determination and a deep neural network for parameter learning. The proposed solution is shown to be feasible for replacing a selected behavioral module in a well-established RoboCup base team, Gliders2d, in which behavioral modules have been evolved with human experts in the loop. Furthermore, we introduce an additional performance-correlated signal (a delayed reward signal), enabling a search for local maxima during a training phase. The extension is compared against a known benchmark. Finally, we investigate the extent to which preserving the structure of expert-designed behaviors affects the performance of a neural network-based solution.
Item Type: | Article |
---|---|
Subjects: | Middle Asian Archive > Mathematical Science |
Depositing User: | Managing Editor |
Date Deposited: | 30 Jun 2023 05:43 |
Last Modified: | 19 Jun 2024 12:34 |
URI: | http://library.eprintglobalarchived.com/id/eprint/925 |