# Boolean Decision Rules for Reinforcement Learning Policy Summarisation

arXiv: https://arxiv.org/abs/2207.08651 · HTML: https://mlsanity.com/paper/2207.08651/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 18 Jul 2022.

## Builds on (most cited first, 8 of 8)

- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [Programmatically Interpretable Reinforcement Learning](https://mlsanity.com/paper/1804.02477/) (2018)
- [AI Safety Gridworlds](https://mlsanity.com/paper/1711.09883/) (2017)
- [Trial without Error: Towards Safe Reinforcement Learning via Human Intervention](https://mlsanity.com/paper/1707.05173/) (2017)
- [Boolean Decision Rules via Column Generation](https://mlsanity.com/paper/1805.09901/) (2018)
- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2106.02097/) (2021)
- [Interactive Visualization for Debugging RL](https://mlsanity.com/paper/2008.07331/) (2020)

## Built on by (most cited first, 2 of 2)

- [AutoDOViz: Human-Centered Automation for Decision Optimization](https://mlsanity.com/paper/2302.09688/) (2023)
- [From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL](https://mlsanity.com/paper/2503.10509/) (2025)

## Abstract (arXiv)

Explainability of Reinforcement Learning (RL) policies remains a challenging research problem, particularly when considering RL in a safety context. Understanding the decisions and intentions of an RL policy offer avenues to incorporate safety into the policy by limiting undesirable actions. We propose the use of a Boolean Decision Rules model to create a post-hoc rule-based summary of an agent's policy. We evaluate our proposed approach using a DQN agent trained on an implementation of a lava gridworld and show that, given a hand-crafted feature representation of this gridworld, simple generalised rules can be created, giving a post-hoc explainable summary of the agent's policy. We discuss possible avenues to introduce safety into a RL agent's policy by using rules generated by this rule-based model as constraints imposed on the agent's policy, as well as discuss how creating simple rule summaries of an agent's policy may help in the debugging process of RL agents.