Sheela
Sheela
Home
Add
Questions
Thinkers
Claims
People
Concepts
Jargon
Sources
Health
Predictions
Collections
Domain Landscape
Contribute
Review
Dedup
Topic requests
Settings
Help

← Jargon

Jargonmachine learning· 2 claims· 1 episode

prior knowledge

Pre-existing abstract knowledge about the world that a pretrained model brings, enabling fast learning of new tasks.

As defined in Fully autonomous robots are much closer than you think – Sergey Levine


Where it comes up · 1
  • Fully autonomous robots are much closer than you think – Sergey Levine2 claims

Most important claims · 2 of 2Search all claims for “prior knowledge” →
  • The single biggest benefit recent AI innovations give to robotics is the ability to leverage prior knowledge: pretrained LLMs and VLMs supply abstracted knowledge about the world (identifying objects, locating things in images) from many sources, which is more important than the fact that the underlying model architecture is shared.Fully autonomous robots are much closer than you think – Sergey Levine
  • Although RL is in principle better than imitation learning, current models use imitation/supervised learning first because effective learning from one's own experience requires already knowing something about the task; supervised learning builds the prior-knowledge foundation that lets the model later figure things out quickly via RL, mirroring how LLMs go from next-token prediction to RL.Fully autonomous robots are much closer than you think – Sergey Levine