# Missing Bridges: Composition-Aware Active Imitation Learning

arXiv: https://arxiv.org/abs/2609.18004 · HTML: https://mlsanity.com/paper/2609.18004/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 11 of 11)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Model-Based Imitation Learning for Urban Driving](https://mlsanity.com/paper/2210.07729/) (2022)
- [ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning](https://mlsanity.com/paper/2109.08273/) (2021)
- [A Comparative Survey of Deep Active Learning](https://mlsanity.com/paper/2203.13450/) (2022)
- [Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings](https://mlsanity.com/paper/1806.02813/) (2018)
- [Zero-shot Imitation Learning by Latent Topology Mapping](https://mlsanity.com/paper/2605.08450/) (2026)

## Abstract (arXiv)

Active imitation learning reduces expert effort by allowing a learner to request the demonstrations it needs. Existing methods typically select these requests for their expected information gain about the expert policy. In structured multi-task domains, however, the number of start-goal tasks may grow combinatorially despite their solutions sharing reusable behavior. This makes composable behaviors especially valuable, since a single demonstration may help solve many tasks at once. Prior methods do not explicitly account for this value when selecting which demonstration to request. We introduce Adaptive Agents via Latent Topologies (AALT), which requests demonstrations that maximize expected gains in start-goal connectivity. We further show that this objective is formally tied to information gain about task reachability. AALT organizes existing demonstrations into a topology of latent hub states connected by learned behaviors, identifies high-value bridge demonstrations that are likely to enable many tasks at once, and grounds each to an expert query. At inference, it plans through the resulting topology and conditions a diffusion policy on each successive hub transition. In a simulated UR5e robot ordered-retrieval domain with 72 tasks, AALT improved from 42/72 to 72/72 (100%) successful tasks consistently using only 3 demonstrations totaling 5 transitions beyond the initial dataset. After 20 demonstrations, the strongest baseline averaged 88.6% success using 98 transitions.