IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation
Diffusion Policy, while outperforming single-step Flow Matching.We validate our approach across diverse manipulation tasks in simulated and real-world environments, showcasing its ability to capture complex behaviours under data constraints.
Authors
- Krishan Rana (ORCID: https://orcid.org/0000-0002-9028-9295)
- David Pershouse
- Robert Lee (ORCID: https://orcid.org/0000-0002-2525-3552)
- Niko Suenderhauf
Publication Details
- Published
- 2025-06-21
- DOI
- https://doi.org/10.15607/rss.2025.xxi.158
- Primary Topic
- Neonatal and fetal brain pathology
- Type
- article
- Field-Weighted Citation Impact
- 0.00