RESEARCH PAPERYear 2019
Diversity is all you need: Learning skills without a reward function
Classification
View four quadrants- Major category
- Foundational work
- Quadrant
- Not applicable
- Architecture
- Not applicable
- Prediction paradigm
- Not applicable
- Subcategories
- Action policy foundationsTheory & planning
- Source review status
- Explicit in survey
Category review. DIAYN is a pre-2026 model-free unsupervised skill-learning foundation using intrinsic discrimination reward and SAC. It learns state-feedback policies without a future-world model and belongs in action-policy/theory background, not generic latent-action components inferred from the word skill. Reading evidence
Contribution
A contribution summary has not been added yet.
Abstract
An abstract has not been added yet.
Affiliations
Not listed in the collection.