# Robust Policy Optimization with Baseline Guarantees

arXiv: https://arxiv.org/abs/1506.04514 · HTML: https://mlsanity.com/paper/1506.04514/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2015.

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

- [Leveraging Factored Action Spaces for Off-Policy Evaluation](https://mlsanity.com/paper/2307.07014/) (2023)
- [Concept-driven Off Policy Evaluation](https://mlsanity.com/paper/2411.19395/) (2024)
- [When Machine Learning Meets Importance Sampling: A More Efficient Rare Event Estimation Approach](https://mlsanity.com/paper/2504.13982/) (2025)

## Abstract (arXiv)

Our goal is to compute a policy that guarantees improved return over a baseline policy even when the available MDP model is inaccurate. The inaccurate model may be constructed, for example, by system identification techniques when the true model is inaccessible. When the modeling error is large, the standard solution to the constructed model has no performance guarantees with respect to the true model. In this paper we develop algorithms that provide such performance guarantees and show a trade-off between their complexity and conservatism. Our novel model-based safe policy search algorithms leverage recent advances in robust optimization techniques. Furthermore we illustrate the effectiveness of these algorithms using a numerical example.