# Automatic Discovery of Interpretable Planning Strategies

arXiv: https://arxiv.org/abs/2005.11730 · HTML: https://mlsanity.com/paper/2005.11730/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2020.

## Built on by (most cited first, 9 of 9)

- [Explainable Deep Reinforcement Learning: State of the Art and Challenges](https://mlsanity.com/paper/2301.09937/) (2023)
- [A Test for Evaluating Performance in Human-Computer Systems](https://mlsanity.com/paper/2206.12390/) (2022)
- [Reinforcement Learning in Practice: Opportunities and Challenges](https://mlsanity.com/paper/2202.11296/) (2022)
- [Boosting human decision-making with AI-generated decision aids](https://mlsanity.com/paper/2203.02776/) (2022)
- [Embodied Navigation with Auxiliary Task of Action Description Prediction](https://mlsanity.com/paper/2510.21809/) (2025)
- [Automatic Discovery and Description of Human Planning Strategies](https://mlsanity.com/paper/2109.14493/) (2021)
- [An intelligent tutor for planning in large partially observable environments](https://mlsanity.com/paper/2302.02785/) (2023)
- [Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer](https://mlsanity.com/paper/2302.09273/) (2023)
- [Explaining Reinforcement Learning Decisions in Self-adaptive Systems](https://mlsanity.com/paper/2608.14620/) (2026)

## Abstract (arXiv)

When making decisions, people often overlook critical information or are overly swayed by irrelevant information. A common approach to mitigate these biases is to provide decision-makers, especially professionals such as medical doctors, with decision aids, such as decision trees and flowcharts. Designing effective decision aids is a difficult problem. We propose that recently developed reinforcement learning methods for discovering clever heuristics for good decision-making can be partially leveraged to assist human experts in this design process. One of the biggest remaining obstacles to leveraging the aforementioned methods is that the policies they learn are opaque to people. To solve this problem, we introduce AI-Interpret: a general method for transforming idiosyncratic policies into simple and interpretable descriptions. Our algorithm combines recent advances in imitation learning and program induction with a new clustering method for identifying a large subset of demonstrations that can be accurately described by a simple, high-performing decision rule. We evaluate our new algorithm and employ it to translate information-acquisition policies discovered through metalevel reinforcement learning. The results of large behavioral experiments showed that prividing the decision rules generated by AI-Interpret as flowcharts significantly improved people's planning strategies and decisions across three diferent classes of sequential decision problems. Moreover, another experiment revealed that this approach is significantly more effective than training people by giving them performance feedback. Finally, a series of ablation studies confirmed that AI-Interpret is critical to the discovery of interpretable decision rules. We conclude that the methods and findings presented herein are an important step towards leveraging automatic strategy discovery to improve human decision-making.