# Interpretable Control by Reinforcement Learning

arXiv: https://arxiv.org/abs/2007.09964 · HTML: https://mlsanity.com/paper/2007.09964/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Learning Interpretable, High-Performing Policies for Autonomous Driving](https://mlsanity.com/paper/2202.02352/) (2022)
- [Model-based Offline Quantum Reinforcement Learning](https://mlsanity.com/paper/2404.10017/) (2024)
- [Synthesizing Interpretable Control Policies through Large Language Model Guided Search](https://mlsanity.com/paper/2410.05406/) (2024)
- [Model-based Policy Optimization using Symbolic World Model](https://mlsanity.com/paper/2407.13518/) (2024)
- [Trustworthy AI for Process Automation on a Chylla-Haase Polymerization Reactor](https://mlsanity.com/paper/2108.13381/) (2021)

## Abstract (arXiv)

In this paper, three recently introduced reinforcement learning (RL) methods are used to generate human-interpretable policies for the cart-pole balancing benchmark. The novel RL methods learn human-interpretable policies in the form of compact fuzzy controllers and simple algebraic equations. The representations as well as the achieved control performances are compared with two classical controller design methods and three non-interpretable RL methods. All eight methods utilize the same previously generated data batch and produce their controller offline - without interaction with the real benchmark dynamics. The experiments show that the novel RL methods are able to automatically generate well-performing policies which are at the same time human-interpretable. Furthermore, one of the methods is applied to automatically learn an equation-based policy for a hardware cart-pole demonstrator by using only human-player-generated batch data. The solution generated in the first attempt already represents a successful balancing policy, which demonstrates the methods applicability to real-world problems.