# Beyond Mimicry: Toward Lifelong Adaptability in Imitation Learning

arXiv: https://arxiv.org/abs/2602.19930 · HTML: https://mlsanity.com/paper/2602.19930/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 23 Feb 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, 6 of 6)

- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Compositionality decomposed: how do neural networks generalise?](https://mlsanity.com/paper/1908.08351/) (2019)
- [Contextual Markov Decision Processes](https://mlsanity.com/paper/1502.02259/) (2015)
- [Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap](https://mlsanity.com/paper/2103.03236/) (2021)
- [A Survey of Imitation Learning Methods, Environments and Metrics](https://mlsanity.com/paper/2404.19456/) (2024)
- [GRAIL: Goal Recognition Alignment through Imitation Learning](https://mlsanity.com/paper/2602.14252/) (2026)

## Abstract (arXiv)

Imitation learning stands at a crossroads: despite decades of progress, current imitation learning agents remain sophisticated memorisation machines, excelling at replay but failing when contexts shift or goals evolve. This paper argues that this failure is not technical but foundational: imitation learning has been optimised for the wrong objective. We propose a research agenda that redefines success from perfect replay to compositional adaptability. Such adaptability hinges on learning behavioural primitives once and recombining them through novel contexts without retraining. We establish metrics for compositional generalisation, propose hybrid architectures, and outline interdisciplinary research directions drawing on cognitive science and cultural evolution. Agents that embed adaptability at the core of imitation learning thus have an essential capability for operating in an open-ended world.