Historical milestone · 2023
RT-2
Reviewed through September 18, 2026
2023 · Historical milestone
RT-2
- Era
- 2020s
- Theme
- Embodied AI & world models
- Evidence form
- Robot-learning experiment
- School / paradigm
- Vision-language-action learning
- Institution / context
- Google DeepMind
- Researchers
- Anthony Brohan; collaborators
Understand
Plain-language record, transferred from the reviewed source module.
Theory or experimental setup. Co-fine-tuned vision-language models on robot trajectories and web-scale image-language data, representing actions as tokens.
Result / historical claim. Reported transfer to novel tabletop instructions and improved semantic generalization over the earlier robot policy.
Apply
Professional implication, only where the reviewed record states one.
The checked-in record does not state a separate professional application for this entry. The topic page places it in the wider research lineage: Embodied AI and world models.
Verify
Evidence status, stated limitations, and the external sources this record actually carries.
Evidence form. Robot-learning experiment
Limitation / debate. Evidence was bounded to particular robot embodiments, datasets, latency, and safety conditions.
Source status. The source link below is the verified link our reviewed topic research already carries for this milestone.
Reproduce
A reproduction tutorial is linked only when one exists for this exact record.
A reproduction tutorial is not yet available for this entry. The closest reviewed material is Embodied AI and world models.
Cite or share
APA-like: This historical record carries a year only, and no author or publisher of record in the checked-in data. An APA reference would have to invent that metadata.
BibTeX: BibTeX requires an author and publication venue. Historical lineage entries store a narrative record and its source link, not structured authorship, so the field would be fabricated.