Beyond Mimicry: Toward Lifelong Adaptability in Imitation Learning
On the map: Offline RL and imitation learning from data → Imitation learning methods
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.
Key facts. No citing papers in the map yet (data through 7 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.
Builds on
6 of 21 references.
Closest ancestors · 3
Same direction, newest first
- 2026GRAIL: Goal Recognition Alignment through Imitation Learning15 Feb
- 2024A Survey of Imitation Learning Methods, Environments and Metrics30 Apr
- 2021Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap4 Mar
Other references · 3
- 2017Hindsight Experience Replaycited by 1,096
- 2019Compositionality decomposed: how do neural networks generalise?cited by 264
- 2015Contextual Markov Decision Processescited by 213
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2021Imitation Learning: Progress, Taxonomies and Challenges
- 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
- 2025Quantifying Generalisation in Imitation Learning
- 2026Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustment
- 2025A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search
- 2024Online Adaptation for Enhancing Imitation Learning Policies
- 2024The intrinsic motivation of reinforcement and imitation learning for sequential tasks
- 2020Bridging the Imitation Gap by Adaptive Insubordination