Frontiers of Information Technology & Electronic Engineering
>> 2022,
Volume 23,
Issue 7
doi:
10.1631/FITEE.2100594
Coach-assisted multi-agent reinforcement learning framework for unexpected crashed agents
Affiliation(s): School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China; College of Intelligence and Computing, Tianjin University, Tianjin 300072, China; less
Received: 2021-12-31
Accepted: 2022-07-21
Available online: 2022-07-21
Next
Previous
Abstract
Multi-agent is difficult to apply in practice, partially because of the gap between simulated and real-world scenarios. One reason for the gap is that simulated systems always assume that agents can work normally all the time, while in practice, one or more agents may unexpectedly "crash" during the coordination process due to inevitable hardware or software failures. Such crashes destroy the cooperation among agents and lead to performance degradation. In this work, we present a formal conceptualization of a cooperative multi-agent system with unexpected crashes. To enhance the robustness of the system to crashes, we propose a coach-assisted multi-agent framework that introduces a virtual coach agent to adjust the crash rate during training. We have designed three coaching strategies (fixed crash rate, curriculum learning, and adaptive crash rate) and a re-sampling strategy for our coach agent. To our knowledge, this work is the first to study unexpected crashes in a . Extensive experiments on grid-world and StarCraft II micromanagement tasks demonstrate the efficacy of the adaptive strategy compared with the fixed crash rate strategy and curriculum learning strategy. The ablation study further illustrates the effectiveness of our re-sampling strategy.
京公网安备 11010502051620号
