# Learning Interpretable, High-Performing Policies for Autonomous Driving

arXiv: https://arxiv.org/abs/2202.02352 · HTML: https://mlsanity.com/paper/2202.02352/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 32 of its 68 references that are in the map.
- First posted on arXiv 4 Feb 2022.

## Placed in

- End-to-end autonomous driving / [Reinforcement learning for driving](https://mlsanity.com/driving/reinforcement-learning-for-driving/)

## Builds on (most cited first, 30 of 32)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks](https://mlsanity.com/paper/1702.01135/) (2017)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [A Survey of Autonomous Driving: Common Practices and Emerging Technologies](https://mlsanity.com/paper/1906.05113/) (2019)
- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [Distilling a Neural Network Into a Soft Decision Tree](https://mlsanity.com/paper/1711.09784/) (2017)
- [Explainable Machine Learning in Deployment](https://mlsanity.com/paper/1909.06342/) (2019)
- [Verifiable Reinforcement Learning via Policy Extraction](https://mlsanity.com/paper/1805.08328/) (2018)
- [Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model](https://mlsanity.com/paper/1511.01644/) (2015)
- [Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention](https://mlsanity.com/paper/1703.10631/) (2017)
- [Grounding Visual Explanations](https://mlsanity.com/paper/1807.09685/) (2018)
- [Beyond Sparsity: Tree Regularization of Deep Models for Interpretability](https://mlsanity.com/paper/1711.06178/) (2017)
- [Adaptive Neural Trees](https://mlsanity.com/paper/1807.06699/) (2018)
- [Learning Certifiably Optimal Rule Lists for Categorical Data](https://mlsanity.com/paper/1704.01701/) (2017)
- [Generating Counterfactual Explanations with Natural Language](https://mlsanity.com/paper/1806.09809/) (2018)
- [Robustness Verification of Tree-based Models](https://mlsanity.com/paper/1906.03849/) (2019)
- [Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations](https://mlsanity.com/paper/1906.06397/) (2019)
- [Regional Tree Regularization for Interpretability in Black Box Models](https://mlsanity.com/paper/1908.04494/) (2019)
- [Mo"ET: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning](https://mlsanity.com/paper/1906.06717/) (2019)
- [Scalable Multiagent Driving Policies For Reducing Traffic Congestion](https://mlsanity.com/paper/2103.00058/) (2021)
- [An Optimization Approach to Learning Falling Rule Lists](https://mlsanity.com/paper/1710.02572/) (2017)
- [Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning](https://mlsanity.com/paper/1902.06007/) (2019)

## Built on by (most cited first, 11 of 11)

- [Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Driving](https://mlsanity.com/paper/2403.12176/) (2024)
- [Advancing Explainable Autonomous Vehicle Systems: A Comprehensive Review and Research Roadmap](https://mlsanity.com/paper/2404.00019/) (2024)
- [Exploring Latent Pathways: Enhancing the Interpretability of Autonomous Driving with a Variational Autoencoder](https://mlsanity.com/paper/2404.01750/) (2024)
- [Optimizing Interpretable Decision Tree Policies for Reinforcement Learning](https://mlsanity.com/paper/2408.11632/) (2024)
- [KnowPC: Knowledge-Driven Programmatic Reinforcement Learning for Zero-shot Coordination](https://mlsanity.com/paper/2408.04336/) (2024)
- [Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies](https://mlsanity.com/paper/2605.17204/) (2026)
- [In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search](https://mlsanity.com/paper/2409.03260/) (2024)
- [Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models](https://mlsanity.com/paper/2503.16724/) (2025)
- [ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies](https://mlsanity.com/paper/2607.07235/) (2026)
- [ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation](https://mlsanity.com/paper/2607.17861/) (2026)
- [Temporally Interpretable Differentiable Decision Trees](https://mlsanity.com/paper/2610.10367/) (2026)

## Abstract (arXiv)

Gradient-based approaches in reinforcement learning (RL) have achieved tremendous success in learning policies for autonomous vehicles. While the performance of these approaches warrants real-world adoption, these policies lack interpretability, limiting deployability in the safety-critical and legally-regulated domain of autonomous driving (AD). AD requires interpretable and verifiable control policies that maintain high performance. We propose Interpretable Continuous Control Trees (ICCTs), a tree-based model that can be optimized via modern, gradient-based, RL approaches to produce high-performing, interpretable policies. The key to our approach is a procedure for allowing direct optimization in a sparse decision-tree-like representation. We validate ICCTs against baselines across six domains, showing that ICCTs are capable of learning interpretable policy representations that parity or outperform baselines by up to 33% in AD scenarios while achieving a 300x-600x reduction in the number of policy parameters against deep learning baselines. Furthermore, we demonstrate the interpretability and utility of our ICCTs through a 14-car physical robot demonstration.