Narrow Results

In multi-agent systems (MAS), the interactions and credit allocation among agents are essential for achieving efficient cooperation. To enhance the interactivity and efficiency of credit allocation in multi-agent reinforcement learning, we introduce a credit allocation for interactive multi-agents method (CAIM). CAIM not only considers the effects of various actions on other agents but also leverages attention mechanisms to handle the mismatch between observations and actions. With a unique credit allocation strategy, agents can more precisely assess their contributions during collaboration. Experiments in various adversarial scenarios within the SMAC benchmark environment indicate that CAIM markedly outperforms existing multi-agent reinforcement learning approaches. Further ablation studies confirm the effectiveness of each CAIM component. This research presents a new paradigm for enhancing collaboration efficiency and overall performance in MAS.

This paper utilizes a countrywide process of county-to-city upgrading in the 1990s to identify whether extending the powers of urban local governments leads to better firm outcomes. The paper hypothesizes that since local leaders in newly promoted cities have an incentive to utilize their new administrative remit to maximize gross domestic product and employment, there should be improvements in economic outcomes. In fact, aggregate firm-level outcomes do not necessarily improve after county-to-city graduation. However, state-owned enterprises perform better after graduation, with increased access to credit through state-owned banks as a possible explanation. Importantly, newly promoted cities with high capacity generally produce better aggregate firm outcomes compared with newly promoted cities with low capacity. The conclusions are twofold. First, relaxing credit constraints for firms could lead to large increases in their operations and employment. Second, increasing local government's administrative remit is not enough to lead to better firm and economic outcomes; local capacity is of paramount importance.