Interpretability for Conditional Coordinated Behavior in Multi-Agent Reinforcement Learning
This work addresses interpretability in multi-agent systems, which is crucial for researchers and practitioners, but it appears incremental as it builds on existing attention-based methods.
The paper tackles the problem of interpreting conditional coordinated behaviors in multi-agent reinforcement learning by proposing a model-free architecture that reuses saliency vectors for conditional states, resulting in agents that learn situation-dependent coordination and achieve superior performance in an objects collection game.
We propose a model-free reinforcement learning architecture, called distributed attentional actor architecture after conditional attention (DA6-X), to provide better interpretability of conditional coordinated behaviors. The underlying principle involves reusing the saliency vector, which represents the conditional states of the environment, such as the global position of agents. Hence, agents with DA6-X flexibility built into their policy exhibit superior performance by considering the additional information in the conditional states during the decision-making process. The effectiveness of the proposed method was experimentally evaluated by comparing it with conventional methods in an objects collection game. By visualizing the attention weights from DA6-X, we confirmed that agents successfully learn situation-dependent coordinated behaviors by correctly identifying various conditional states, leading to improved interpretability of agents along with superior performance.