Optimizing Interpretable Decision Tree Policies For Reinforcement Learning

Abstract

Reinforcement learning techniques leveraging deep learning have made tremendous progress in recent years. However, the complexity of neural networks prevents practitioners from understanding their behavior. Decision trees have gained increased attention in supervised learning for their inherent interpretability, enabling modelers to understand the exact prediction process after learning. This paper considers the problem of optimizing interpretable decision tree policies to replace neural networks in reinforcement learning settings. Previous works have relaxed the tree structure, restricted to optimizing only tree leaves, or applied imitation learning techniques to approximately copy the behavior of a neural network policy with a decision tree. We propose the Decision Tree Policy Optimization (DTPO) algorithm that directly optimizes the complete decision tree using policy gradients. Our technique uses established decision tree heuristics for regression to perform policy optimization. We

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyvos2024optimizing

Related papers

• CDT: Cascading Decision Trees For Explainable Reinforcement Learning (2020)0.00
• Mitigating Information Loss In Tree-based Reinforcement Learning Via Direct Optimization (2024)0.00
• "so, Tell Me About Your Policy...": Distillation Of Interpretable Policies From Deep Reinforcement Learning Agents (2025)0.00
• Iterative Bounding Mdps: Learning Interpretable Policies Via Non-interpretable Methods (2021)0.00
• Interpretable Local Tree Surrogate Policies (2021)0.00
• Verifiable Reinforcement Learning Via Policy Extraction (2018)0.00
• MAVIPER: Learning Decision Tree Policies For Interpretable Multi-agent Reinforcement Learning (2022)5.84
• Improved Exploration Through Latent Trajectory Optimization In Deep Deterministic Policy Gradient (2019)0.00