# Learning Programmatically Structured Representations with Perceptor Gradients

arXiv: https://arxiv.org/abs/1905.00956 · HTML: https://mlsanity.com/paper/1905.00956/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2019.

## Built on by (most cited first, 3 of 3)

- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning](https://mlsanity.com/paper/2407.15786/) (2024)
- [Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization](https://mlsanity.com/paper/2408.08761/) (2024)

## Abstract (arXiv)

We present the perceptor gradients algorithm -- a novel approach to learning symbolic representations based on the idea of decomposing an agent's policy into i) a perceptor network extracting symbols from raw observation data and ii) a task encoding program which maps the input symbols to output actions. We show that the proposed algorithm is able to learn representations that can be directly fed into a Linear-Quadratic Regulator (LQR) or a general purpose A* planner. Our experimental results confirm that the perceptor gradients algorithm is able to efficiently learn transferable symbolic representations as well as generate new observations according to a semantically meaningful specification.