ME‐MADDPG: An efficient learning‐based motion planning method for multiple agents in complex environments
Journal article
Wan, K., Wu, D., Li, B., Gao, X., Hu, Z. and Chen, D. (2021). ME‐MADDPG: An efficient learning‐based motion planning method for multiple agents in complex environments. International Journal of Intelligent Systems. 37 (3), pp. 2393-2427. https://doi.org/10.1002/int.22778
Authors | Wan, K., Wu, D., Li, B., Gao, X., Hu, Z. and Chen, D. |
---|---|
Abstract | Developing efficient motion policies for multi-agents is a challenge in a decentralized dynamic situation, where each agent plans its own paths without knowing the policies of the other agents involved. This paper presents an efficient learning-based motion planning method for multi-agent systems. It adopts the framework of multi-agent deep deterministic policy gradient (MADDPG) to directly map partially observed information to motion commands for multiple agents. To improve the efficiency of MADDPG in sample utilization, so as to train more brilliant agents that can adapt to more complex environments, a strategy named mixing experience (ME) is introduced to MADDPG, and this has led to our proposed ME-MADDPG algorithm. The novel ME strategy can be embodied into three specific mechanisms: 1) An artificial potential field (APF) based sample generator to produce high-quality samples in the early training stage; 2) A dynamic mixed sampling strategy to mix the training data from different sources with a variable proportion; 3) A delayed learning skill to stabilize the training of the multiple agents. A series of experiments have been conducted to verify the performance of the proposed ME-MADDPG algorithm, and it has been demonstrated that, compared with MADDPG, the proposed algorithm can significantly improve the convergence speed and convergence effect in the training process, and it has also shown better efficiency and better adaptability in complex dynamic environments while it is used for multi-agent motion planning applications. |
Keywords | Artificial Intelligence; Human-Computer Interaction; Theoretical Computer Science; Software |
Year | 2021 |
Journal | International Journal of Intelligent Systems |
Journal citation | 37 (3), pp. 2393-2427 |
Publisher | Wiley |
ISSN | 0884-8173 |
1098-111X | |
Digital Object Identifier (DOI) | https://doi.org/10.1002/int.22778 |
Funder/Client | Natural Science Foundation of Shaanxi Province |
Publication dates | |
Online | 09 Dec 2021 |
Publication process dates | |
Accepted | 02 Oct 2021 |
Deposited | 18 Mar 2022 |
Accepted author manuscript | License File Access Level Open |
Additional information | This is the peer reviewed version of the following article: ME-MADDPG: An efficient learning-based motion planning method for multiple agents in complex environments, which has been published in final form at https://onlinelibrary.wiley.com/doi/10.1002/int.22778. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions. This article may not be enhanced, enriched or otherwise transformed into a derivative work, without express permission from Wiley or by statutory rights under applicable legislation. Copyright notices must not be removed, obscured or modified. The article must be linked to Wiley’s version of record on Wiley Online Library and any embedding, framing or otherwise making available the article or pages thereof by third parties from platforms, services and websites other than Wiley Online Library must be prohibited. |
License | http://onlinelibrary.wiley.com/termsAndConditions#vor |
https://openresearch.lsbu.ac.uk/item/8yw24
Download files
237
total views68
total downloads0
views this month0
downloads this month