Graph Convolutional Reinforcement Learning
This work addresses the challenge of cooperation in dynamic multi-agent systems, which is crucial for applications like robotics and game AI, but it appears incremental as it builds on existing graph and reinforcement learning techniques.
The paper tackled the problem of learning cooperation in dynamic multi-agent environments by proposing graph convolutional reinforcement learning, which adapts to changing agent relationships and uses relation kernels to capture interplay, resulting in substantial performance improvements over existing methods in various cooperative scenarios.
Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors change quickly. This makes it hard to learn abstract representations of mutual interplay between agents. To tackle these difficulties, we propose graph convolutional reinforcement learning, where graph convolution adapts to the dynamics of the underlying graph of the multi-agent environment, and relation kernels capture the interplay between agents by their relation representations. Latent features produced by convolutional layers from gradually increased receptive fields are exploited to learn cooperation, and cooperation is further improved by temporal relation regularization for consistency. Empirically, we show that our method substantially outperforms existing methods in a variety of cooperative scenarios.