Mixrts: Toward Interpretable Multi-agent Reinforcement Learning Via Mixing Recurrent Soft Decision Trees

Abstract

While achieving tremendous success in various fields, existing multi-agent reinforcement learning (MARL) with a black-box neural network makes decisions in an opaque manner that hinders humans from understanding the learned knowledge and how input observations influence decisions. In contrast, existing interpretable approaches usually suffer from weak expressivity and low performance. To bridge this gap, we propose MIXing Recurrent soft decision Trees (MIXRTs), a novel interpretable architecture that can represent explicit decision processes via the root-to-leaf path and reflect each agent's contribution to the team. Specifically, we construct a novel soft decision tree using a recurrent structure and demonstrate which features influence the decision-making process. Then, based on the value decomposition framework, we linearly assign credit to each agent by explicitly mixing individual action values to estimate the joint action value using only local observations, providing new insight

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keyliu2022mixrts

Related papers

• MAVIPER: Learning Decision Tree Policies For Interpretable Multi-agent Reinforcement Learning (2022)5.84
• AIIR-MIX: Multi-agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network (2023)0.00
• MAGIC-MASK: Multi-agent Guided Inter-agent Collaboration With Mask-based Explainability For Reinforcement Learning (2025)0.00
• CDT: Cascading Decision Trees For Explainable Reinforcement Learning (2020)0.00
• Multi-agent Reinforcement Learning Via Adaptive Kalman Temporal Difference And Successor Representation (2021)0.00
• Perspectives For Direct Interpretability In Multi-agent Deep Reinforcement Learning (2025)0.00
• Boosting Value Decomposition Via Unit-wise Attentive State Representation For Cooperative Multi-agent Reinforcement Learning (2023)0.00
• Decentralized Multi-agent Reinforcement Learning With Networked Agents: Recent Advances (2019)0.00