# Temporally Interpretable Differentiable Decision Trees

arXiv: https://arxiv.org/abs/2610.10367 · HTML: https://mlsanity.com/paper/2610.10367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 47 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 13 of 13)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Reinforcement Learning with Action Chunking](https://mlsanity.com/paper/2507.07969/) (2025)
- [Gymnasium: A Standard Interface for Reinforcement Learning Environments](https://mlsanity.com/paper/2407.17032/) (2024)
- [XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models](https://mlsanity.com/paper/2407.15248/) (2024)
- [Decoupled Q-Chunking](https://mlsanity.com/paper/2512.10926/) (2025)
- [Robust Policy Optimization in Deep Reinforcement Learning](https://mlsanity.com/paper/2212.07536/) (2022)
- [Learning Interpretable, High-Performing Policies for Autonomous Driving](https://mlsanity.com/paper/2202.02352/) (2022)
- [Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models](https://mlsanity.com/paper/1606.05320/) (2016)
- [Optimization Methods for Interpretable Differentiable Decision Trees in Reinforcement Learning](https://mlsanity.com/paper/1903.09338/) (2019)

## Abstract (arXiv)

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.