# Reward Bound for Behavioral Guarantee of Model-based Planning Agents

arXiv: https://arxiv.org/abs/2402.13419 · HTML: https://mlsanity.com/paper/2402.13419/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 9 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 3 of 3)

- [Algorithms for Verifying Deep Neural Networks](https://mlsanity.com/paper/1903.06758/) (2019)
- [Safely Entering the Deep: A Review of Verification and Validation for Machine Learning and a Challenge Elicitation in the Automotive Industry](https://mlsanity.com/paper/1812.05389/) (2018)
- [ALAN: Autonomously Exploring Robotic Agents in the Real World](https://mlsanity.com/paper/2302.06604/) (2023)

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

- [Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control](https://mlsanity.com/paper/2403.00172/) (2024)
- [A Safe and Data-efficient Model-based Reinforcement Learning System for HVAC Control](https://mlsanity.com/paper/2407.12195/) (2024)
- [MARLP: Time-series Forecasting Control for Agricultural Managed Aquifer Recharge](https://mlsanity.com/paper/2407.01005/) (2024)

## Abstract (arXiv)

Recent years have seen an emerging interest in the trustworthiness of machine learning-based agents in the wild, especially in robotics, to provide safety assurance for the industry. Obtaining behavioral guarantees for these agents remains an important problem. In this work, we focus on guaranteeing a model-based planning agent reaches a goal state within a specific future time step. We show that there exists a lower bound for the reward at the goal state, such that if the said reward is below that bound, it is impossible to obtain such a guarantee. By extension, we show how to enforce preferences over multiple goals.