# Efficient Imitation Learning with Conservative World Models

arXiv: https://arxiv.org/abs/2405.13193 · HTML: https://mlsanity.com/paper/2405.13193/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 41 of its 48 references that are in the map.
- First posted on arXiv 21 May 2024.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)
- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 30 of 41)

- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [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)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [MOReL : Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2005.05951/) (2020)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [COMBO: Conservative Offline Model-Based Policy Optimization](https://mlsanity.com/paper/2102.08363/) (2021)
- [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020)
- [Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images](https://mlsanity.com/paper/1506.07365/) (2015)
- [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021)
- [Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model](https://mlsanity.com/paper/1907.00953/) (2019)
- [Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning](https://mlsanity.com/paper/1809.02925/) (2018)
- [IQ-Learn: Inverse soft-Q Learning for Imitation](https://mlsanity.com/paper/2106.12142/) (2021)
- [A Divergence Minimization Perspective on Imitation Learning Methods](https://mlsanity.com/paper/1911.02256/) (2019)
- [A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models](https://mlsanity.com/paper/1611.03852/) (2016)
- [Model-Based Imitation Learning for Urban Driving](https://mlsanity.com/paper/2210.07729/) (2022)
- [Model-Based Offline Planning](https://mlsanity.com/paper/2008.05556/) (2020)
- [Imitation Learning as f-Divergence Minimization](https://mlsanity.com/paper/1905.12888/) (2019)
- [Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization](https://mlsanity.com/paper/2006.03647/) (2020)
- [Offline Reinforcement Learning from Images with Latent Space Models](https://mlsanity.com/paper/2012.11547/) (2020)
- [Feedback in Imitation Learning: The Three Regimes of Covariate Shift](https://mlsanity.com/paper/2102.02872/) (2021)
- [MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/2212.05698/) (2022)
- [Overcoming Model Bias for Robust Offline Deep Reinforcement Learning](https://mlsanity.com/paper/2008.05533/) (2020)

## Built on by (most cited first, 11 of 11)

- [Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures](https://mlsanity.com/paper/2505.00779/) (2025)
- [Simulating the Visual World with Artificial Intelligence: A Roadmap](https://mlsanity.com/paper/2511.08585/) (2025)
- [Four Principles for Physically Interpretable World Models](https://mlsanity.com/paper/2503.02143/) (2025)
- [Reward-free World Models for Online Imitation Learning](https://mlsanity.com/paper/2410.14081/) (2024)
- [Sample-Efficient Behavior Cloning Using General Domain Knowledge](https://mlsanity.com/paper/2501.16546/) (2025)
- [Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning](https://mlsanity.com/paper/2510.09487/) (2025)
- [Learning from Demonstrations via Capability-Aware Goal Sampling](https://mlsanity.com/paper/2601.08731/) (2026)
- [Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms](https://mlsanity.com/paper/2605.01778/) (2026)
- [Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning](https://mlsanity.com/paper/2505.02228/) (2025)
- [Latent Wasserstein Adversarial Imitation Learning](https://mlsanity.com/paper/2603.05440/) (2026)
- [Beyond Conservatism: Recoverability-Conditioned Exploration for Model-Based Imitation Learning](https://mlsanity.com/paper/2609.33336/) (2026)

## Abstract (arXiv)

We tackle the problem of policy learning from expert demonstrations without a reward function. A central challenge in this space is that these policies fail upon deployment due to issues of distributional shift, environment stochasticity, or compounding errors. Adversarial imitation learning alleviates this issue but requires additional on-policy training samples for stability, which presents a challenge in realistic domains due to inefficient learning and high sample complexity. One approach to this issue is to learn a world model of the environment, and use synthetic data for policy training. While successful in prior works, we argue that this is sub-optimal due to additional distribution shifts between the learned model and the real environment. Instead, we re-frame imitation learning as a fine-tuning problem, rather than a pure reinforcement learning one. Drawing theoretical connections to offline RL and fine-tuning algorithms, we argue that standard online world model algorithms are not well suited to the imitation learning problem. We derive a principled conservative optimization bound and demonstrate empirically that it leads to improved performance on two very challenging manipulation environments from high-dimensional raw pixel observations. We set a new state-of-the-art performance on the Franka Kitchen environment from images, requiring only 10 demos on no reward labels, as well as solving a complex dexterity manipulation task.