# Revealing the Challenges of Sim-to-Real Transfer in Model-Based Reinforcement Learning via Latent Space Modeling

arXiv: https://arxiv.org/abs/2506.12735 · HTML: https://mlsanity.com/paper/2506.12735/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 15 Jun 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 23 of 23)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [One-Shot Visual Imitation Learning via Meta-Learning](https://mlsanity.com/paper/1709.04905/) (2017)
- [Deep Reinforcement Learning framework for Autonomous Driving](https://mlsanity.com/paper/1704.02532/) (2017)
- [Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience](https://mlsanity.com/paper/1810.05687/) (2018)
- [Active Domain Randomization](https://mlsanity.com/paper/1904.04762/) (2019)
- [RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2204.12581/) (2022)
- [When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning](https://mlsanity.com/paper/2206.13464/) (2022)
- [Waymo Public Road Safety Performance Data](https://mlsanity.com/paper/2011.00038/) (2020)
- [H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps](https://mlsanity.com/paper/2309.12716/) (2023)
- [Improving Offline Reinforcement Learning with Inaccurate Simulators](https://mlsanity.com/paper/2405.04307/) (2024)

## Built on by (most cited first, 1 of 1)

- [The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective](https://mlsanity.com/paper/2606.07017/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) is playing an increasingly important role in fields such as robotic control and autonomous driving. However, the gap between simulation and the real environment remains a major obstacle to the practical deployment of RL. Agents trained in simulators often struggle to maintain performance when transferred to real-world physical environments. In this paper, we propose a latent space based approach to analyze the impact of simulation on real-world policy improvement in model-based settings. As a natural extension of model-based methods, our approach enables an intuitive observation of the challenges faced by model-based methods in sim-to-real transfer. Experiments conducted in the MuJoCo environment evaluate the performance of our method in both measuring and mitigating the sim-to-real gap. The experiments also highlight the various challenges that remain in overcoming the sim-to-real gap, especially for model-based methods.