# Towards Generalisable Imitation Learning Through Conditioned Transition Estimation and Online Behaviour Alignment

arXiv: https://arxiv.org/abs/2601.17563 · HTML: https://mlsanity.com/paper/2601.17563/

## Key facts

- Cited by 1 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.
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 24 Jan 2026.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [IQ-Learn: Inverse soft-Q Learning for Imitation](https://mlsanity.com/paper/2106.12142/) (2021)
- [Generative Adversarial Imitation from Observation](https://mlsanity.com/paper/1807.06158/) (2018)
- [Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap](https://mlsanity.com/paper/2103.03236/) (2021)
- [Off-Policy Imitation Learning from Observations](https://mlsanity.com/paper/2102.13185/) (2021)
- [MobILE: Model-Based Imitation Learning From Observation Alone](https://mlsanity.com/paper/2102.10769/) (2021)

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

- [When in Doubt, Plan It Out: Committed Small Language Model Deliberation for Reactive Reinforcement Learning](https://mlsanity.com/paper/2606.16995/) (2026)

## Abstract (arXiv)

State-of-the-art imitation learning from observation methods (ILfO) have recently made significant progress, but they still have some limitations: they need action-based supervised optimisation, assume that states have a single optimal action, and tend to apply teacher actions without full consideration of the actual environment state. While the truth may be out there in observed trajectories, existing methods struggle to extract it without supervision. In this work, we propose Unsupervised Imitation Learning from Observation (UfO) that addresses all of these limitations. UfO learns a policy through a two-stage process, in which the agent first obtains an approximation of the teacher's true actions in the observed state transitions, and then refines the learned policy further by adjusting agent trajectories to closely align them with the teacher's. Experiments we conducted in five widely used environments show that UfO not only outperforms the teacher and all other ILfO methods but also displays the smallest standard deviation. This reduction in standard deviation indicates better generalisation in unseen scenarios.