HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning
This addresses the challenge of reducing human workload and improving scalability in multi-agent reinforcement learning for group-oriented tasks, though it appears incremental by building on existing human-in-the-loop methods.
The paper tackles the problem of scaling human-in-the-loop reinforcement learning to multi-agent group tasks by proposing HARP, a framework that integrates automatic agent regrouping with strategic human assistance during deployment, enabling non-experts to provide effective guidance with minimal intervention and enhancing performance in collaboration scenarios.
Human-in-the-loop reinforcement learning integrates human expertise to accelerate agent learning and provide critical guidance and feedback in complex fields. However, many existing approaches focus on single-agent tasks and require continuous human involvement during the training process, significantly increasing the human workload and limiting scalability. In this paper, we propose HARP (Human-Assisted Regrouping with Permutation Invariant Critic), a multi-agent reinforcement learning framework designed for group-oriented tasks. HARP integrates automatic agent regrouping with strategic human assistance during deployment, enabling and allowing non-experts to offer effective guidance with minimal intervention. During training, agents dynamically adjust their groupings to optimize collaborative task completion. When deployed, they actively seek human assistance and utilize the Permutation Invariant Group Critic to evaluate and refine human-proposed groupings, allowing non-expert users to contribute valuable suggestions. In multiple collaboration scenarios, our approach is able to leverage limited guidance from non-experts and enhance performance. The project can be found at https://github.com/huawen-hu/HARP.