# Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model

arXiv: https://arxiv.org/abs/2406.09976 · HTML: https://mlsanity.com/paper/2406.09976/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Latent dynamics models and model-based RL, one of 11 directions in World models.
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Placed in

- World models / [Latent dynamics models and model-based RL](https://mlsanity.com/wm/latent-dynamics-models-and-model-based-rl/)
- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 16 of 16)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey](https://mlsanity.com/paper/2009.13303/) (2020)
- [RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2204.12581/) (2022)
- [Online Robust Reinforcement Learning with Model Uncertainty](https://mlsanity.com/paper/2109.14523/) (2021)
- [Sim-to-Real Robot Learning from Pixels with Progressive Nets](https://mlsanity.com/paper/1610.04286/) (2016)
- [Policy Gradient Method For Robust Reinforcement Learning](https://mlsanity.com/paper/2205.07344/) (2022)
- [Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model](https://mlsanity.com/paper/1610.03518/) (2016)
- [Policy Gradient for Rectangular Robust Markov Decision Processes](https://mlsanity.com/paper/2301.13589/) (2023)
- [Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning](https://mlsanity.com/paper/2301.12593/) (2023)
- [Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel](https://mlsanity.com/paper/2306.05859/) (2023)

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

- [Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2502.02844/) (2025)
- [Evaluating Robustness of Reinforcement Learning Algorithms for Autonomous Shipping](https://mlsanity.com/paper/2411.04915/) (2024)
- [A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learning](https://mlsanity.com/paper/2606.16933/) (2026)

## Abstract (arXiv)

Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and safety in the learned policies. More specifically, an RL agent that trains in a certain Markov decision process (MDP) often struggles to perform well in nearly identical MDPs. To address this issue, we employ the framework of Robust MDPs (RMDPs) in a model-based setting and introduce a novel learned transition model. Our method specifically incorporates an auxiliary pessimistic model, updated adversarially, to estimate the worst-case MDP within a Kullback-Leibler uncertainty set. In comparison to several existing works, our work does not impose any additional conditions on the training environment, such as the need for a parametric simulator. To test the effectiveness of the proposed pessimistic model in enhancing policy robustness, we integrate it into a practical RL algorithm, called Robust Model-Based Policy Optimization (RMBPO). Our experimental results indicate a notable improvement in policy robustness on high-dimensional MuJoCo control tasks, with the auxiliary model enhancing the performance of the learned policy in distorted MDPs. We further explore the learned deviation between the proposed auxiliary world model and the nominal model, to examine how pessimism is achieved. By learning a pessimistic world model and demonstrating its role in improving policy robustness, our research contributes towards making (model-based) RL more robust.