# Imitating Latent Policies from Observation

arXiv: https://arxiv.org/abs/1805.07914 · HTML: https://mlsanity.com/paper/1805.07914/

## Key facts

- Cited by 101 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 21 May 2018.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Built on by (most cited first, 30 of 101)

- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges](https://mlsanity.com/paper/2309.02473/) (2023)
- [Primal Wasserstein Imitation Learning](https://mlsanity.com/paper/2006.04678/) (2020)
- [Learning to Act without Actions](https://mlsanity.com/paper/2312.10812/) (2023)
- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026)
- [AdaWorld: Learning Adaptable World Models with Latent Actions](https://mlsanity.com/paper/2503.18938/) (2025)
- [Reinforcement Learning with Action-Free Pre-Training from Videos](https://mlsanity.com/paper/2203.13880/) (2022)
- [XIRL: Cross-embodiment Inverse Reinforcement Learning](https://mlsanity.com/paper/2106.03911/) (2021)
- [Recent Advances in Imitation Learning from Observation](https://mlsanity.com/paper/1905.13566/) (2019)
- [State-Only Imitation Learning for Dexterous Manipulation](https://mlsanity.com/paper/2004.04650/) (2020)
- [Video as the New Language for Real-World Decision Making](https://mlsanity.com/paper/2402.17139/) (2024)
- [Provably Efficient Imitation Learning from Observation Alone](https://mlsanity.com/paper/1905.10948/) (2019)
- [State Alignment-based Imitation Learning](https://mlsanity.com/paper/1911.10947/) (2019)
- [Off-Policy Imitation Learning from Observations](https://mlsanity.com/paper/2102.13185/) (2021)
- [Imitation Learning: Progress, Taxonomies and Challenges](https://mlsanity.com/paper/2106.12177/) (2021)
- [Learning Latent Action World Models In The Wild](https://mlsanity.com/paper/2601.05230/) (2026)
- [MobILE: Model-Based Imitation Learning From Observation Alone](https://mlsanity.com/paper/2102.10769/) (2021)
- [DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control](https://mlsanity.com/paper/2409.12192/) (2024)
- [Latent Action Learning Requires Supervision in the Presence of Distractors](https://mlsanity.com/paper/2502.00379/) (2025)
- [Provable Representation Learning for Imitation Learning via Bi-level Optimization](https://mlsanity.com/paper/2002.10544/) (2020)
- [Towards Generalist Robot Learning from Internet Video: A Survey](https://mlsanity.com/paper/2404.19664/) (2024)
- [What Do Latent Action Models Actually Learn?](https://mlsanity.com/paper/2506.15691/) (2025)
- [Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models](https://mlsanity.com/paper/2204.02392/) (2022)
- [NitroGen: An Open Foundation Model for Generalist Gaming Agents](https://mlsanity.com/paper/2601.02427/) (2026)
- [Latent Diffusion Planning for Imitation Learning](https://mlsanity.com/paper/2504.16925/) (2025)
- [Imitation Learning from Video by Leveraging Proprioception](https://mlsanity.com/paper/1905.09335/) (2019)

## Abstract (arXiv)

In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of latent actions on observations while simultaneously predicting their likelihood. We then outline an action alignment procedure that leverages a small amount of environment interactions to determine a mapping between the latent and real-world actions. We show that this corrected labeling can be used for imitating the observed behavior, even though no expert actions are given. We evaluate our approach within classic control environments and a platform game and demonstrate that it performs better than standard approaches. Code for this work is available at https://github.com/ashedwards/ILPO.