Deep reinforcement learning for urban multi-taxis cruising strategy

Guo, Weian; Hua, Zhenyao; Kang, Zecheng; Li, Dongyang; Wang, Lei; Wu, Qidi; Lerch, Alexander

doi:10.1007/s00521-022-07255-9

Cited by 1 publication

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to recent research [1][2][3], multiple categories of XRL provide the interpretability of agents. For example, the decision-making process of agents has been interpreted by decomposing reward functions [4][5][6][7] or visualizing their saliency maps based on the integrated gradients method [8][9][10][11]. The attention mechanism and transformer developed by Vaswani et al [12] also play a critical role in providing transparency to the decision-making process.…”

Section: Introductionmentioning

confidence: 99%

eDA3-X: Distributed Attentional Actor Architecture for Interpretability of Coordinated Behaviors in Multi-Agent Systems

Motokawa

Sugawara

2023

Applied Sciences

View full text Add to dashboard Cite

In this paper, we propose an enhanced version of the distributed attentional actor architecture (eDA3-X) for model-free reinforcement learning. This architecture is designed to facilitate the interpretability of learned coordinated behaviors in multi-agent systems through the use of a saliency vector that captures partial observations of the environment. Our proposed method, in principle, can be integrated with any deep reinforcement learning method, as indicated by X, and can help us identify the information in input data that individual agents attend to during and after training. We then validated eDA3-X through experiments in the object collection game. We also analyzed the relationship between cooperative behaviors and three types of attention heatmaps (standard, positional, and class attentions), which provided insight into the information that the agents consider crucial when making decisions. In addition, we investigated how attention is developed by an agent through training experiences. Our experiments indicate that our approach offers a promising solution for understanding coordinated behaviors in multi-agent reinforcement learning.

show abstract