Tacit Learning with Adaptive Information Selection for Cooperative Multi-Agent Reinforcement Learning
This addresses cooperative decision-making problems in multi-agent systems with communication limitations, representing an incremental advancement in MARL frameworks.
The paper tackles the challenges of centralized training with decentralized execution in multi-agent reinforcement learning by introducing a framework that enables agents to develop implicit coordination and adaptively filter information, resulting in significant performance improvements when integrated with state-of-the-art algorithms.
In multi-agent reinforcement learning (MARL), the centralized training with decentralized execution (CTDE) framework has gained widespread adoption due to its strong performance. However, the further development of CTDE faces two key challenges. First, agents struggle to autonomously assess the relevance of input information for cooperative tasks, impairing their decision-making abilities. Second, in communication-limited scenarios with partial observability, agents are unable to access global information, restricting their ability to collaborate effectively from a global perspective. To address these challenges, we introduce a novel cooperative MARL framework based on information selection and tacit learning. In this framework, agents gradually develop implicit coordination during training, enabling them to infer the cooperative behavior of others in a discrete space without communication, relying solely on local information. Moreover, we integrate gating and selection mechanisms, allowing agents to adaptively filter information based on environmental changes, thereby enhancing their decision-making capabilities. Experiments on popular MARL benchmarks show that our framework can be seamlessly integrated with state-of-the-art algorithms, leading to significant performance improvements.