Interpretability For Conditional Coordinated Behavior In Multi-agent Reinforcement Learning

Abstract

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.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keymotokawa2023interpretability

Related papers

• Distributed Multi-agent Deep Reinforcement Learning For Robust Coordination Against Noise (2022)5.84
• Actor-attention-critic For Multi-agent Reinforcement Learning (2018)0.00
• Attention-guided Contrastive Role Representations For Multi-agent Reinforcement Learning (2023)3.64
• Interpretable Learning Dynamics In Unsupervised Reinforcement Learning (2025)0.00
• Attention Actor-critic Algorithm For Multi-agent Constrained Co-operative Reinforcement Learning (2021)0.00
• Visual Explanation Using Attention Mechanism In Actor-critic-based Deep Reinforcement Learning (2021)10.21
• Promoting Coordination Through Policy Regularization In Multi-agent Deep Reinforcement Learning (2019)0.00
• Sa-matd3:self-attention-based Multi-agent Continuous Control Method In Cooperative Environments (2021)11.76