# Adding Neural Network Controllers to Behavior Trees without Destroying Performance Guarantees

arXiv: https://arxiv.org/abs/1809.10283 · HTML: https://mlsanity.com/paper/1809.10283/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2018.

## Built on by (most cited first, 6 of 6)

- [Behavior Trees in Robot Control Systems](https://mlsanity.com/paper/2203.13083/) (2022)
- [A Study on Training and Developing Large Language Models for Behavior Tree Generation](https://mlsanity.com/paper/2401.08089/) (2024)
- [Continuous-Time Behavior Trees as Discontinuous Dynamical Systems](https://mlsanity.com/paper/2109.01575/) (2021)
- [An Extended Convergence Result for Behaviour Tree Controllers](https://mlsanity.com/paper/2308.08994/) (2023)
- [Behavior Trees Enable Structured Programming of Language Model Agents](https://mlsanity.com/paper/2404.07439/) (2024)
- [Combining Reinforcement Learning and Behavior Trees for NPCs in Video Games with AMD Schola](https://mlsanity.com/paper/2510.14154/) (2025)

## Abstract (arXiv)

In this paper, we show how Behavior Trees that have performance guarantees, in terms of safety and goal convergence, can be extended with components that were designed using machine learning, without destroying those performance guarantees. Machine learning approaches such as reinforcement learning or learning from demonstration can be very appealing to AI designers that want efficient and realistic behaviors in their agents. However, those algorithms seldom provide guarantees for solving the given task in all different situations while keeping the agent safe. Instead, such guarantees are often easier to find for manually designed model-based approaches. In this paper we exploit the modularity of behavior trees to extend a given design with an efficient, but possibly unreliable, machine learning component in a way that preserves the guarantees. The approach is illustrated with an inverted pendulum example.