Temporally Interpretable Differentiable Decision Trees
cs.LG, cs.RO
Submitted: 2026-10-07
Updated: 2026-10-07
Code: https://github.com/ei5uke/temp-interp
License: http://creativecommons.org/licenses/by/4.0/
The gist: Interpretability offers a solution to safe autonomy by providing transparency into an agent's underlying decision-making model.
Terminology
Abstract
Interpretability offers a solution to safe autonomy by providing transparency into an agent's underlying decision-making model. Within sequential-decision making tasks, differentiable decision trees (DDTs) are one approach to such interpretability, maintaining automatic-differentiable policies while providing humans with a discrete tree-based visualization. Nonetheless, current implementations of DDTs are not well-suited for sequential-decision making domains, as there exists an inherent mismatch between a tree's single-timestep behavior and a human's multi-timestep planning. Our work thus introduces time as a new dimension of interpretability, coined as temporal interpretability, and demonstrates how temporal abstractions via action chunking improve it. We achieve this by first introducing two novel policy gradient algorithms that incorporate action chunking. Additionally, to maintain parameter-efficient trees, we develop an information-theoretic tree restructuring algorithm that modifies the tree during training. Across four simulation environments, we find that warm-starting action chunked DDTs from a distilled action chunked policy is the most effective way to obtain temporally interpretable trees: they match neural network policies in three of the four domains while using up to 80 % fewer parameters. Our code is available at https://github.com/ei5uke/temp-interp.
Sources
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models
- Towards A Rigorous Science of Interpretable Machine Learning
- Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models
- Decoupled Q-Chunking
- Reinforcement Learning with Action Chunking
- Representation Learning with Contrastive Predictive Coding
- Learning Interpretable, High-Performing Policies for Autonomous Driving
- Robust Policy Optimization in Deep Reinforcement Learning
- Opening the Black Box of Deep Neural Networks via Information
- Optimization Methods for Interpretable Differentiable Decision Trees in Reinforcement Learning
- Gymnasium: A Standard Interface for Reinforcement Learning Environments
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks