Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study introduces a novel approach to multi-agent deep reinforcement learning that allows for selective human control over specific agents while enabling uninstructed agents to autonomously complement their actions. By addressing the limitations of traditional coordination methods, which often fail to align with human expectations, the proposed method enhances the adaptability and overall performance of multi-agent systems in dynamic environments. Experimental results demonstrate that agents utilizing this strategy outperform those relying on conventional coordination techniques, highlighting the effectiveness of targeted instruction combined with autonomous task completion.
Agents can now autonomously adapt their actions based on selective human instructions, leading to superior coordination and performance in multi-agent systems.
This study proposes a learning method for multi-agent systems that allows agents to be controlled through human manager instructions after learning and enables uninstructed agents to implicitly complement the overall work based on the actions of other agents. Multi-agent applications using deep learning have shown potential; thus, to achieve extensive social applications, humans should be able to control learned agents using simple methods to respond to environmental and social changes. Even without such changes, learned coordination often does not match the expectations of human managers, making it preferable to control coordination structures to match human intentions. Some studies have aimed to control agent behavior using simple instructions. However, they assumed that instructions are provided to all agents, which is time-consuming and not evident when designing a better cooperation regime. Ideally, specific agents should receive key action instructions, while others should automatically complete the remaining tasks. The proposed method, which extends previous work on controllability in multi-agent deep reinforcement learning, enables uninstructed agents to adaptively complement overlooked tasks and areas. The experimental results show that agents using the proposed method can shift to another cooperative structure and achieve better performance than those using conventional methods.