# Learning Behavior Trees with Genetic Programming in Unpredictable Environments

arXiv: https://arxiv.org/abs/2011.03252 · HTML: https://mlsanity.com/paper/2011.03252/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2020.

## Built on by (most cited first, 7 of 7)

- [Behavior Trees in Robot Control Systems](https://mlsanity.com/paper/2203.13083/) (2022)
- [Combining Planning and Learning of Behavior Trees for Robotic Assembly](https://mlsanity.com/paper/2103.09036/) (2021)
- [A Study on Training and Developing Large Language Models for Behavior Tree Generation](https://mlsanity.com/paper/2401.08089/) (2024)
- [Designing Robust Cyber-Defense Agents with Evolving Behavior Trees](https://mlsanity.com/paper/2410.16383/) (2024)
- [EvolvingBehavior: Towards Co-Creative Evolution of Behavior Trees for Game NPCs](https://mlsanity.com/paper/2209.01020/) (2022)
- [BeSimulator: A Large Language Model Powered Text-based Behavior Simulator](https://mlsanity.com/paper/2409.15865/) (2024)
- [Composition Machines: Programming Self-Organising Software Models for the Emergence of Sequential Program Spaces](https://mlsanity.com/paper/2108.05402/) (2021)

## Abstract (arXiv)

Modern industrial applications require robots to be able to operate in unpredictable environments, and programs to be created with a minimal effort, as there may be frequent changes to the task. In this paper, we show that genetic programming can be effectively used to learn the structure of a behavior tree (BT) to solve a robotic task in an unpredictable environment. Moreover, we propose to use a simple simulator for the learning and demonstrate that the learned BTs can solve the same task in a realistic simulator, reaching convergence without the need for task specific heuristics. The learned solution is tolerant to faults, making our method appealing for real robotic applications.