3 accepted papers
This letter presents a novel method to solve the decentralized task allocation problem for large-scale multi-agent systems (MASs), with an emphasis on communication efficiency. Conventional methods typically depend on sharing the localized task allocation plans of various agents across a communicati
This letter proposes a novel consensus-based timetable algorithm (CBTA) to solve the decentralized simultaneous multi-agent task allocation problem. Due to the limited capability of each agent, multiple agents may be required to perform a task simultaneously. A key challenge is how to meet the requi
Multi-hop machine reading comprehension (MRC) task aims to enable models to answer the compound question according to the bridging information. Existing methods that use graph neural networks to represent multiple granularities such as entities and sentences in documents update all nodes synchronous…